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

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

Neuron 3942 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2337. Min Range: -3.2337

Max Act: 3.2337. Min Act: -0.0000

Data Index: 593701 (C4 (Web Text))

Max Activating Token Index: 773

Text #1

Max Range: 3.2337. Min Range: -3.2337

Max Act: 2.5473. Min Act: -0.0001

Data Index: 201142 (C4 (Web Text))

Max Activating Token Index: 591

Text #2

Max Range: 3.2337. Min Range: -3.2337

Max Act: 2.7780. Min Act: -0.0001

Data Index: 879597 (C4 (Web Text))

Max Activating Token Index: 932

Text #3

Max Range: 3.2337. Min Range: -3.2337

Max Act: 2.3791. Min Act: -0.0001

Data Index: 1076506 (C4 (Web Text))

Max Activating Token Index: 339

Text #4

Max Range: 3.2337. Min Range: -3.2337

Max Act: 2.5528. Min Act: -0.0001

Data Index: 1058553 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 3.2337. Min Range: -3.2337

Max Act: 2.3661. Min Act: -0.0001

Data Index: 1174612 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 3.2337. Min Range: -3.2337

Max Act: 2.3558. Min Act: -0.0001

Data Index: 1075020 (C4 (Web Text))

Max Activating Token Index: 227

Text #7

Max Range: 3.2337. Min Range: -3.2337

Max Act: 2.4530. Min Act: -0.0001

Data Index: 977945 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 3.2337. Min Range: -3.2337

Max Act: 2.5076. Min Act: -0.0001

Data Index: 732205 (C4 (Web Text))

Max Activating Token Index: 869

Text #9

Max Range: 3.2337. Min Range: -3.2337

Max Act: 2.1955. Min Act: -0.0001

Data Index: 832286 (C4 (Web Text))

Max Activating Token Index: 862

Text #10

Max Range: 3.2337. Min Range: -3.2337

Max Act: 2.4179. Min Act: -0.0001

Data Index: 1183468 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 3.2337. Min Range: -3.2337

Max Act: 2.5294. Min Act: -0.0001

Data Index: 696899 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 3.2337. Min Range: -3.2337

Max Act: 2.2783. Min Act: -0.0000

Data Index: 995299 (C4 (Web Text))

Max Activating Token Index: 413

Text #13

Max Range: 3.2337. Min Range: -3.2337

Max Act: 2.3846. Min Act: -0.0000

Data Index: 270344 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 3.2337. Min Range: -3.2337

Max Act: 2.2458. Min Act: -0.0001

Data Index: 1319902 (C4 (Web Text))

Max Activating Token Index: 790

Text #15

Max Range: 3.2337. Min Range: -3.2337

Max Act: 2.1251. Min Act: -0.0000

Data Index: 903033 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 3.2337. Min Range: -3.2337

Max Act: 2.0150. Min Act: -0.0001

Data Index: 1158140 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 3.2337. Min Range: -3.2337

Max Act: 2.2433. Min Act: -0.0001

Data Index: 1155147 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 3.2337. Min Range: -3.2337

Max Act: 2.2417. Min Act: -0.0001

Data Index: 1082631 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 3.2337. Min Range: -3.2337

Max Act: 2.2193. Min Act: -0.0001

Data Index: 1226748 (C4 (Web Text))

Max Activating Token Index: 478