< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 21 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: 2.1280. Min Range: -2.1280

Max Act: 2.1280. Min Act: -0.0001

Data Index: 1983392 (The Pile)

Max Activating Token Index: 923

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.1280. Min Range: -2.1280

Max Act: 1.5373. Min Act: -0.0001

Data Index: 943933 (The Pile)

Max Activating Token Index: 185

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.1280. Min Range: -2.1280

Max Act: 1.4902. Min Act: -0.0001

Data Index: 1648129 (The Pile)

Max Activating Token Index: 21

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.1280. Min Range: -2.1280

Max Act: 1.4474. Min Act: -0.0001

Data Index: 1824995 (The Pile)

Max Activating Token Index: 76

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.1280. Min Range: -2.1280

Max Act: 1.4564. Min Act: -0.0001

Data Index: 1929472 (The Pile)

Max Activating Token Index: 17

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.1280. Min Range: -2.1280

Max Act: 1.3107. Min Act: -0.0001

Data Index: 1864150 (The Pile)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.1280. Min Range: -2.1280

Max Act: 1.3040. Min Act: -0.0001

Data Index: 1631277 (The Pile)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.1280. Min Range: -2.1280

Max Act: 1.2396. Min Act: -0.0001

Data Index: 1445403 (The Pile)

Max Activating Token Index: 405

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.1280. Min Range: -2.1280

Max Act: 1.3138. Min Act: -0.0001

Data Index: 419684 (The Pile)

Max Activating Token Index: 863

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.1280. Min Range: -2.1280

Max Act: 1.2292. Min Act: -0.0001

Data Index: 323138 (The Pile)

Max Activating Token Index: 436

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.1280. Min Range: -2.1280

Max Act: 1.2300. Min Act: -0.0001

Data Index: 1191481 (The Pile)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.1280. Min Range: -2.1280

Max Act: 1.1327. Min Act: -0.0001

Data Index: 531731 (The Pile)

Max Activating Token Index: 322

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.1280. Min Range: -2.1280

Max Act: 1.1263. Min Act: -0.0001

Data Index: 575289 (The Pile)

Max Activating Token Index: 172

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.1280. Min Range: -2.1280

Max Act: 1.2059. Min Act: -0.0001

Data Index: 1791095 (The Pile)

Max Activating Token Index: 935

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.1280. Min Range: -2.1280

Max Act: 1.1651. Min Act: -0.0001

Data Index: 422784 (The Pile)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.1280. Min Range: -2.1280

Max Act: 1.1267. Min Act: -0.0001

Data Index: 840551 (The Pile)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.1280. Min Range: -2.1280

Max Act: 1.0473. Min Act: -0.0001

Data Index: 734791 (The Pile)

Max Activating Token Index: 284

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.1280. Min Range: -2.1280

Max Act: 1.0805. Min Act: -0.0001

Data Index: 1908991 (The Pile)

Max Activating Token Index: 201

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.1280. Min Range: -2.1280

Max Act: 1.2020. Min Act: -0.0001

Data Index: 852269 (The Pile)

Max Activating Token Index: 38

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.1280. Min Range: -2.1280

Max Act: 1.0899. Min Act: -0.0001

Data Index: 1947385 (The Pile)

Max Activating Token Index: 187

Click toggle to see full text

Truncated

Full Text #19