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

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

Neuron 252 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4183. Min Range: -0.4183

Max Act: 0.4183. Min Act: -0.0000

Data Index: 507948 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 0.4183. Min Range: -0.4183

Max Act: 0.3637. Min Act: -0.0000

Data Index: 1188084 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 0.4183. Min Range: -0.4183

Max Act: 0.3536. Min Act: -0.0000

Data Index: 504872 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 0.4183. Min Range: -0.4183

Max Act: 0.3240. Min Act: -0.0000

Data Index: 292765 (C4 (Web Text))

Max Activating Token Index: 950

Text #4

Max Range: 0.4183. Min Range: -0.4183

Max Act: 0.3395. Min Act: -0.0000

Data Index: 67803 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 0.4183. Min Range: -0.4183

Max Act: 0.3232. Min Act: -0.0000

Data Index: 280630 (C4 (Web Text))

Max Activating Token Index: 1002

Text #6

Max Range: 0.4183. Min Range: -0.4183

Max Act: 0.2948. Min Act: -0.0000

Data Index: 995327 (C4 (Web Text))

Max Activating Token Index: 317

Text #7

Max Range: 0.4183. Min Range: -0.4183

Max Act: 0.3257. Min Act: -0.0000

Data Index: 1161178 (C4 (Web Text))

Max Activating Token Index: 419

Text #8

Max Range: 0.4183. Min Range: -0.4183

Max Act: 0.3074. Min Act: -0.0000

Data Index: 917444 (C4 (Web Text))

Max Activating Token Index: 825

Text #9

Max Range: 0.4183. Min Range: -0.4183

Max Act: 0.3171. Min Act: -0.0000

Data Index: 631395 (C4 (Web Text))

Max Activating Token Index: 560

Text #10

Max Range: 0.4183. Min Range: -0.4183

Max Act: 0.3169. Min Act: -0.0000

Data Index: 1192341 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 0.4183. Min Range: -0.4183

Max Act: 0.2871. Min Act: -0.0000

Data Index: 487871 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 0.4183. Min Range: -0.4183

Max Act: 0.2655. Min Act: -0.0000

Data Index: 401316 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 0.4183. Min Range: -0.4183

Max Act: 0.2551. Min Act: -0.0000

Data Index: 1160379 (C4 (Web Text))

Max Activating Token Index: 145

Text #14

Max Range: 0.4183. Min Range: -0.4183

Max Act: 0.2716. Min Act: -0.0000

Data Index: 868128 (C4 (Web Text))

Max Activating Token Index: 586

Text #15

Max Range: 0.4183. Min Range: -0.4183

Max Act: 0.2588. Min Act: -0.0000

Data Index: 430448 (C4 (Web Text))

Max Activating Token Index: 93

Text #16

Max Range: 0.4183. Min Range: -0.4183

Max Act: 0.2638. Min Act: -0.0000

Data Index: 591336 (C4 (Web Text))

Max Activating Token Index: 325

Text #17

Max Range: 0.4183. Min Range: -0.4183

Max Act: 0.2258. Min Act: -0.0000

Data Index: 521417 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 0.4183. Min Range: -0.4183

Max Act: 0.2271. Min Act: -0.0000

Data Index: 1260718 (C4 (Web Text))

Max Activating Token Index: 684

Text #19

Max Range: 0.4183. Min Range: -0.4183

Max Act: 0.2522. Min Act: -0.0000

Data Index: 863179 (C4 (Web Text))

Max Activating Token Index: 439