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

Dataset: The Pile

Neuron 1895 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.6197. Min Act: -0.0000

Data Index: 1451286 (The Pile)

Max Activating Token Index: 395

Text #1

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.5397. Min Act: -0.0000

Data Index: 344798 (The Pile)

Max Activating Token Index: 154

Text #2

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4907. Min Act: -0.0000

Data Index: 885248 (The Pile)

Max Activating Token Index: 748

Text #3

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.5010. Min Act: -0.0000

Data Index: 1092919 (The Pile)

Max Activating Token Index: 399

Text #4

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.5120. Min Act: -0.0000

Data Index: 237890 (The Pile)

Max Activating Token Index: 967

Text #5

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4883. Min Act: -0.0000

Data Index: 744276 (The Pile)

Max Activating Token Index: 945

Text #6

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4489. Min Act: -0.0000

Data Index: 1844364 (The Pile)

Max Activating Token Index: 30

Text #7

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4645. Min Act: -0.0000

Data Index: 1926711 (The Pile)

Max Activating Token Index: 383

Text #8

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4617. Min Act: -0.0000

Data Index: 78683 (The Pile)

Max Activating Token Index: 234

Text #9

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4554. Min Act: -0.0000

Data Index: 1223273 (The Pile)

Max Activating Token Index: 393

Text #10

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4327. Min Act: -0.0000

Data Index: 804377 (The Pile)

Max Activating Token Index: 946

Text #11

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4294. Min Act: -0.0000

Data Index: 1620628 (The Pile)

Max Activating Token Index: 109

Text #12

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4249. Min Act: -0.0000

Data Index: 1897823 (The Pile)

Max Activating Token Index: 613

Text #13

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4226. Min Act: -0.0000

Data Index: 1425538 (The Pile)

Max Activating Token Index: 601

Text #14

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4057. Min Act: -0.0000

Data Index: 927255 (The Pile)

Max Activating Token Index: 450

Text #15

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4300. Min Act: -0.0000

Data Index: 1192437 (The Pile)

Max Activating Token Index: 705

Text #16

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4123. Min Act: -0.0000

Data Index: 330986 (The Pile)

Max Activating Token Index: 339

Text #17

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4345. Min Act: -0.0000

Data Index: 1310514 (The Pile)

Max Activating Token Index: 772

Text #18

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4056. Min Act: -0.0000

Data Index: 1134552 (The Pile)

Max Activating Token Index: 102

Text #19

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.3964. Min Act: -0.0000

Data Index: 903916 (The Pile)

Max Activating Token Index: 391