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

Dataset: The Pile

Neuron 234 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.5937. Min Act: -0.0000

Data Index: 1270167 (The Pile)

Max Activating Token Index: 283

Text #1

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.5293. Min Act: -0.0000

Data Index: 840257 (The Pile)

Max Activating Token Index: 240

Text #2

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.4655. Min Act: -0.0000

Data Index: 1447388 (The Pile)

Max Activating Token Index: 539

Text #3

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.4616. Min Act: -0.0000

Data Index: 1567423 (The Pile)

Max Activating Token Index: 246

Text #4

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.4540. Min Act: -0.0000

Data Index: 70178 (The Pile)

Max Activating Token Index: 28

Text #5

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.5252. Min Act: -0.0000

Data Index: 943347 (The Pile)

Max Activating Token Index: 677

Text #6

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.4773. Min Act: -0.0000

Data Index: 932887 (The Pile)

Max Activating Token Index: 384

Text #7

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.4570. Min Act: -0.0000

Data Index: 1777517 (The Pile)

Max Activating Token Index: 607

Text #8

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.4508. Min Act: -0.0000

Data Index: 1611072 (The Pile)

Max Activating Token Index: 598

Text #9

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.4843. Min Act: -0.0000

Data Index: 1460880 (The Pile)

Max Activating Token Index: 944

Text #10

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.4446. Min Act: -0.0000

Data Index: 1054183 (The Pile)

Max Activating Token Index: 826

Text #11

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.3910. Min Act: -0.0000

Data Index: 969899 (The Pile)

Max Activating Token Index: 102

Text #12

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.4291. Min Act: -0.0000

Data Index: 832302 (The Pile)

Max Activating Token Index: 82

Text #13

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.4164. Min Act: -0.0000

Data Index: 560503 (The Pile)

Max Activating Token Index: 204

Text #14

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.4395. Min Act: -0.0000

Data Index: 417310 (The Pile)

Max Activating Token Index: 19

Text #15

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.3903. Min Act: -0.0000

Data Index: 131093 (The Pile)

Max Activating Token Index: 292

Text #16

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.3612. Min Act: -0.0000

Data Index: 1350105 (The Pile)

Max Activating Token Index: 453

Text #17

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.3751. Min Act: -0.0000

Data Index: 299550 (The Pile)

Max Activating Token Index: 787

Text #18

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.4318. Min Act: -0.0000

Data Index: 1674844 (The Pile)

Max Activating Token Index: 1007

Text #19

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.3889. Min Act: -0.0000

Data Index: 149463 (The Pile)

Max Activating Token Index: 604