Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4602 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.2437. Min Act: -0.0000

Data Index: 1289556 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.2304. Min Act: -0.0000

Data Index: 481477 (C4 (Web Text))

Max Activating Token Index: 403

Text #2

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.2360. Min Act: -0.0000

Data Index: 634736 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.2123. Min Act: -0.0000

Data Index: 293195 (C4 (Web Text))

Max Activating Token Index: 856

Text #4

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.2099. Min Act: -0.0000

Data Index: 1150938 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.2064. Min Act: -0.0000

Data Index: 692698 (C4 (Web Text))

Max Activating Token Index: 57

Text #6

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.2142. Min Act: -0.0000

Data Index: 636421 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.2048. Min Act: -0.0000

Data Index: 709286 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.2010. Min Act: -0.0000

Data Index: 416899 (C4 (Web Text))

Max Activating Token Index: 598

Text #9

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.2114. Min Act: -0.0000

Data Index: 508817 (C4 (Web Text))

Max Activating Token Index: 120

Text #10

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.2045. Min Act: -0.0000

Data Index: 1040933 (C4 (Web Text))

Max Activating Token Index: 449

Text #11

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.2127. Min Act: -0.0000

Data Index: 576115 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.1972. Min Act: -0.0000

Data Index: 1319466 (C4 (Web Text))

Max Activating Token Index: 411

Text #13

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.1931. Min Act: -0.0000

Data Index: 104752 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.1930. Min Act: -0.0000

Data Index: 353038 (C4 (Web Text))

Max Activating Token Index: 588

Text #15

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.1941. Min Act: -0.0000

Data Index: 841352 (C4 (Web Text))

Max Activating Token Index: 919

Text #16

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.2026. Min Act: -0.0000

Data Index: 524328 (C4 (Web Text))

Max Activating Token Index: 836

Text #17

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.1959. Min Act: -0.0000

Data Index: 902201 (C4 (Web Text))

Max Activating Token Index: 491

Text #18

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.2192. Min Act: -0.0000

Data Index: 719387 (C4 (Web Text))

Max Activating Token Index: 928

Text #19

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.2011. Min Act: -0.0000

Data Index: 1099329 (C4 (Web Text))

Max Activating Token Index: 133