< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 4053 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: 3.1208. Min Range: -3.1208

Max Act: 3.0031. Min Act: -0.0001

Data Index: 376877 (The Pile)

Max Activating Token Index: 632

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.1208. Min Range: -3.1208

Max Act: 2.9454. Min Act: -0.0001

Data Index: 1995083 (The Pile)

Max Activating Token Index: 728

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.1208. Min Range: -3.1208

Max Act: 3.1208. Min Act: -0.0000

Data Index: 39738 (The Pile)

Max Activating Token Index: 763

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.1208. Min Range: -3.1208

Max Act: 2.9881. Min Act: -0.0001

Data Index: 610381 (The Pile)

Max Activating Token Index: 784

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.1208. Min Range: -3.1208

Max Act: 2.8610. Min Act: -0.0001

Data Index: 262903 (The Pile)

Max Activating Token Index: 368

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.1208. Min Range: -3.1208

Max Act: 2.6265. Min Act: -0.0001

Data Index: 572621 (The Pile)

Max Activating Token Index: 509

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.1208. Min Range: -3.1208

Max Act: 2.5144. Min Act: -0.0000

Data Index: 1719748 (The Pile)

Max Activating Token Index: 695

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.1208. Min Range: -3.1208

Max Act: 2.6830. Min Act: -0.0001

Data Index: 1713862 (The Pile)

Max Activating Token Index: 144

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.1208. Min Range: -3.1208

Max Act: 2.6530. Min Act: -0.0001

Data Index: 1015065 (The Pile)

Max Activating Token Index: 689

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.1208. Min Range: -3.1208

Max Act: 2.5826. Min Act: -0.0001

Data Index: 1699036 (The Pile)

Max Activating Token Index: 955

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.1208. Min Range: -3.1208

Max Act: 2.5339. Min Act: -0.0001

Data Index: 1527874 (The Pile)

Max Activating Token Index: 132

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.1208. Min Range: -3.1208

Max Act: 2.6706. Min Act: -0.0001

Data Index: 997113 (The Pile)

Max Activating Token Index: 951

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.1208. Min Range: -3.1208

Max Act: 2.4399. Min Act: -0.0001

Data Index: 225222 (The Pile)

Max Activating Token Index: 19

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.1208. Min Range: -3.1208

Max Act: 2.2972. Min Act: -0.0001

Data Index: 1541074 (The Pile)

Max Activating Token Index: 430

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.1208. Min Range: -3.1208

Max Act: 2.5253. Min Act: -0.0001

Data Index: 448200 (The Pile)

Max Activating Token Index: 373

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.1208. Min Range: -3.1208

Max Act: 2.3839. Min Act: -0.0001

Data Index: 414105 (The Pile)

Max Activating Token Index: 200

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.1208. Min Range: -3.1208

Max Act: 2.2168. Min Act: -0.0001

Data Index: 1867357 (The Pile)

Max Activating Token Index: 168

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.1208. Min Range: -3.1208

Max Act: 2.5068. Min Act: -0.0001

Data Index: 27792 (The Pile)

Max Activating Token Index: 862

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.1208. Min Range: -3.1208

Max Act: 2.3574. Min Act: -0.0001

Data Index: 357458 (The Pile)

Max Activating Token Index: 201

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.1208. Min Range: -3.1208

Max Act: 2.4573. Min Act: -0.0001

Data Index: 1368777 (The Pile)

Max Activating Token Index: 998

Click toggle to see full text

Truncated

Full Text #19