Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1828 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.2279. Min Range: -2.2279

Max Act: 2.2279. Min Act: -0.0000

Data Index: 1113995 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 2.2279. Min Range: -2.2279

Max Act: 2.1630. Min Act: -0.0000

Data Index: 1164875 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 2.2279. Min Range: -2.2279

Max Act: 1.8978. Min Act: -0.0000

Data Index: 866939 (C4 (Web Text))

Max Activating Token Index: 939

Text #3

Max Range: 2.2279. Min Range: -2.2279

Max Act: 1.7706. Min Act: -0.0000

Data Index: 149099 (C4 (Web Text))

Max Activating Token Index: 930

Text #4

Max Range: 2.2279. Min Range: -2.2279

Max Act: 1.7666. Min Act: -0.0000

Data Index: 88998 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 2.2279. Min Range: -2.2279

Max Act: 1.6465. Min Act: -0.0000

Data Index: 286904 (C4 (Web Text))

Max Activating Token Index: 935

Text #6

Max Range: 2.2279. Min Range: -2.2279

Max Act: 1.8550. Min Act: -0.0000

Data Index: 871466 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 2.2279. Min Range: -2.2279

Max Act: 1.5438. Min Act: -0.0000

Data Index: 744614 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 2.2279. Min Range: -2.2279

Max Act: 1.7192. Min Act: -0.0000

Data Index: 762433 (C4 (Web Text))

Max Activating Token Index: 868

Text #9

Max Range: 2.2279. Min Range: -2.2279

Max Act: 1.7223. Min Act: -0.0000

Data Index: 1036721 (C4 (Web Text))

Max Activating Token Index: 132

Text #10

Max Range: 2.2279. Min Range: -2.2279

Max Act: 1.7126. Min Act: -0.0000

Data Index: 513312 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 2.2279. Min Range: -2.2279

Max Act: 1.6710. Min Act: -0.0000

Data Index: 468623 (C4 (Web Text))

Max Activating Token Index: 482

Text #12

Max Range: 2.2279. Min Range: -2.2279

Max Act: 1.5179. Min Act: -0.0000

Data Index: 266932 (C4 (Web Text))

Max Activating Token Index: 795

Text #13

Max Range: 2.2279. Min Range: -2.2279

Max Act: 1.7533. Min Act: -0.0000

Data Index: 159612 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 2.2279. Min Range: -2.2279

Max Act: 1.8292. Min Act: -0.0000

Data Index: 176514 (C4 (Web Text))

Max Activating Token Index: 779

Text #15

Max Range: 2.2279. Min Range: -2.2279

Max Act: 1.6209. Min Act: -0.0000

Data Index: 563651 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 2.2279. Min Range: -2.2279

Max Act: 1.5912. Min Act: -0.0000

Data Index: 436802 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 2.2279. Min Range: -2.2279

Max Act: 1.6842. Min Act: -0.0000

Data Index: 1307919 (C4 (Web Text))

Max Activating Token Index: 435

Text #18

Max Range: 2.2279. Min Range: -2.2279

Max Act: 1.5811. Min Act: -0.0000

Data Index: 116502 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 2.2279. Min Range: -2.2279

Max Act: 1.4590. Min Act: -0.0000

Data Index: 216956 (C4 (Web Text))

Max Activating Token Index: 421