< Prev | Home | Model | Random | Next >

Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 27 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')



Text #0

Max Range: 0.5236. Min Range: -0.5236

Max Act: 0.5236. Min Act: -0.0001

Data Index: 1508119 (The Pile)

Max Activating Token Index: 42

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.5236. Min Range: -0.5236

Max Act: 0.4997. Min Act: -0.0001

Data Index: 1762040 (The Pile)

Max Activating Token Index: 234

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.5236. Min Range: -0.5236

Max Act: 0.4588. Min Act: -0.0001

Data Index: 1964235 (The Pile)

Max Activating Token Index: 538

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.5236. Min Range: -0.5236

Max Act: 0.4530. Min Act: -0.0000

Data Index: 558411 (The Pile)

Max Activating Token Index: 188

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.5236. Min Range: -0.5236

Max Act: 0.4260. Min Act: -0.0001

Data Index: 1830967 (The Pile)

Max Activating Token Index: 215

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.5236. Min Range: -0.5236

Max Act: 0.4578. Min Act: -0.0000

Data Index: 1866141 (The Pile)

Max Activating Token Index: 283

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.5236. Min Range: -0.5236

Max Act: 0.4375. Min Act: -0.0001

Data Index: 253427 (The Pile)

Max Activating Token Index: 117

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.5236. Min Range: -0.5236

Max Act: 0.4216. Min Act: -0.0001

Data Index: 237764 (The Pile)

Max Activating Token Index: 465

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.5236. Min Range: -0.5236

Max Act: 0.4211. Min Act: -0.0001

Data Index: 1825822 (The Pile)

Max Activating Token Index: 597

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.5236. Min Range: -0.5236

Max Act: 0.4173. Min Act: -0.0001

Data Index: 1765495 (The Pile)

Max Activating Token Index: 539

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.5236. Min Range: -0.5236

Max Act: 0.4159. Min Act: -0.0001

Data Index: 624736 (The Pile)

Max Activating Token Index: 610

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.5236. Min Range: -0.5236

Max Act: 0.4261. Min Act: -0.0001

Data Index: 1468639 (The Pile)

Max Activating Token Index: 567

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.5236. Min Range: -0.5236

Max Act: 0.4367. Min Act: -0.0001

Data Index: 1041705 (The Pile)

Max Activating Token Index: 372

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.5236. Min Range: -0.5236

Max Act: 0.4075. Min Act: -0.0001

Data Index: 955336 (The Pile)

Max Activating Token Index: 45

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.5236. Min Range: -0.5236

Max Act: 0.4207. Min Act: -0.0001

Data Index: 1752606 (The Pile)

Max Activating Token Index: 25

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.5236. Min Range: -0.5236

Max Act: 0.4191. Min Act: -0.0001

Data Index: 679161 (The Pile)

Max Activating Token Index: 345

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.5236. Min Range: -0.5236

Max Act: 0.4140. Min Act: -0.0001

Data Index: 1786908 (The Pile)

Max Activating Token Index: 969

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.5236. Min Range: -0.5236

Max Act: 0.4342. Min Act: -0.0001

Data Index: 18843 (The Pile)

Max Activating Token Index: 127

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.5236. Min Range: -0.5236

Max Act: 0.4038. Min Act: -0.0001

Data Index: 1327669 (The Pile)

Max Activating Token Index: 123

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.5236. Min Range: -0.5236

Max Act: 0.4235. Min Act: -0.0001

Data Index: 1638682 (The Pile)

Max Activating Token Index: 161

Click toggle to see full text

Truncated

Full Text #19