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

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

Neuron 1829 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9386. Min Range: -0.9386

Max Act: 0.9386. Min Act: -0.0001

Data Index: 973182 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 0.9386. Min Range: -0.9386

Max Act: 0.8593. Min Act: -0.0002

Data Index: 558050 (C4 (Web Text))

Max Activating Token Index: 958

Text #2

Max Range: 0.9386. Min Range: -0.9386

Max Act: 0.8610. Min Act: -0.0002

Data Index: 816877 (C4 (Web Text))

Max Activating Token Index: 975

Text #3

Max Range: 0.9386. Min Range: -0.9386

Max Act: 0.8220. Min Act: -0.0002

Data Index: 208395 (C4 (Web Text))

Max Activating Token Index: 554

Text #4

Max Range: 0.9386. Min Range: -0.9386

Max Act: 0.8772. Min Act: -0.0002

Data Index: 568907 (C4 (Web Text))

Max Activating Token Index: 164

Text #5

Max Range: 0.9386. Min Range: -0.9386

Max Act: 0.8474. Min Act: -0.0001

Data Index: 454330 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 0.9386. Min Range: -0.9386

Max Act: 0.8851. Min Act: -0.0002

Data Index: 1027666 (C4 (Web Text))

Max Activating Token Index: 731

Text #7

Max Range: 0.9386. Min Range: -0.9386

Max Act: 0.8345. Min Act: -0.0002

Data Index: 395725 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 0.9386. Min Range: -0.9386

Max Act: 0.8191. Min Act: -0.0001

Data Index: 295420 (C4 (Web Text))

Max Activating Token Index: 65

Text #9

Max Range: 0.9386. Min Range: -0.9386

Max Act: 0.8468. Min Act: -0.0002

Data Index: 1249945 (C4 (Web Text))

Max Activating Token Index: 1004

Text #10

Max Range: 0.9386. Min Range: -0.9386

Max Act: 0.8309. Min Act: -0.0002

Data Index: 865465 (C4 (Web Text))

Max Activating Token Index: 712

Text #11

Max Range: 0.9386. Min Range: -0.9386

Max Act: 0.8354. Min Act: -0.0001

Data Index: 877410 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 0.9386. Min Range: -0.9386

Max Act: 0.7848. Min Act: -0.0002

Data Index: 464388 (C4 (Web Text))

Max Activating Token Index: 328

Text #13

Max Range: 0.9386. Min Range: -0.9386

Max Act: 0.7865. Min Act: -0.0002

Data Index: 125753 (C4 (Web Text))

Max Activating Token Index: 1004

Text #14

Max Range: 0.9386. Min Range: -0.9386

Max Act: 0.7999. Min Act: -0.0001

Data Index: 357472 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 0.9386. Min Range: -0.9386

Max Act: 0.7167. Min Act: -0.0001

Data Index: 722637 (C4 (Web Text))

Max Activating Token Index: 172

Text #16

Max Range: 0.9386. Min Range: -0.9386

Max Act: 0.8209. Min Act: -0.0001

Data Index: 684415 (C4 (Web Text))

Max Activating Token Index: 102

Text #17

Max Range: 0.9386. Min Range: -0.9386

Max Act: 0.7329. Min Act: -0.0002

Data Index: 208225 (C4 (Web Text))

Max Activating Token Index: 854

Text #18

Max Range: 0.9386. Min Range: -0.9386

Max Act: 0.7983. Min Act: -0.0001

Data Index: 182910 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 0.9386. Min Range: -0.9386

Max Act: 0.7740. Min Act: -0.0002

Data Index: 1189393 (C4 (Web Text))

Max Activating Token Index: 929