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

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

Neuron 1351 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4393. Min Range: -0.4393

Max Act: 0.4393. Min Act: -0.0000

Data Index: 1245961 (C4 (Web Text))

Max Activating Token Index: 813

Text #1

Max Range: 0.4393. Min Range: -0.4393

Max Act: 0.4123. Min Act: -0.0001

Data Index: 1106561 (C4 (Web Text))

Max Activating Token Index: 701

Text #2

Max Range: 0.4393. Min Range: -0.4393

Max Act: 0.3614. Min Act: -0.0001

Data Index: 1010077 (C4 (Web Text))

Max Activating Token Index: 530

Text #3

Max Range: 0.4393. Min Range: -0.4393

Max Act: 0.3472. Min Act: -0.0001

Data Index: 900708 (C4 (Web Text))

Max Activating Token Index: 284

Text #4

Max Range: 0.4393. Min Range: -0.4393

Max Act: 0.3385. Min Act: -0.0001

Data Index: 1178833 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 0.4393. Min Range: -0.4393

Max Act: 0.3485. Min Act: -0.0001

Data Index: 700902 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 0.4393. Min Range: -0.4393

Max Act: 0.3160. Min Act: -0.0000

Data Index: 1333107 (C4 (Web Text))

Max Activating Token Index: 147

Text #7

Max Range: 0.4393. Min Range: -0.4393

Max Act: 0.3252. Min Act: -0.0000

Data Index: 311787 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 0.4393. Min Range: -0.4393

Max Act: 0.3181. Min Act: -0.0000

Data Index: 969616 (C4 (Web Text))

Max Activating Token Index: 243

Text #9

Max Range: 0.4393. Min Range: -0.4393

Max Act: 0.3398. Min Act: -0.0001

Data Index: 853401 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 0.4393. Min Range: -0.4393

Max Act: 0.3228. Min Act: -0.0001

Data Index: 528788 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 0.4393. Min Range: -0.4393

Max Act: 0.3430. Min Act: -0.0000

Data Index: 1074815 (C4 (Web Text))

Max Activating Token Index: 729

Text #12

Max Range: 0.4393. Min Range: -0.4393

Max Act: 0.3192. Min Act: -0.0001

Data Index: 1163203 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 0.4393. Min Range: -0.4393

Max Act: 0.3413. Min Act: -0.0000

Data Index: 189049 (C4 (Web Text))

Max Activating Token Index: 206

Text #14

Max Range: 0.4393. Min Range: -0.4393

Max Act: 0.3115. Min Act: -0.0001

Data Index: 816091 (C4 (Web Text))

Max Activating Token Index: 651

Text #15

Max Range: 0.4393. Min Range: -0.4393

Max Act: 0.3481. Min Act: -0.0001

Data Index: 824196 (C4 (Web Text))

Max Activating Token Index: 689

Text #16

Max Range: 0.4393. Min Range: -0.4393

Max Act: 0.2857. Min Act: -0.0001

Data Index: 322244 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 0.4393. Min Range: -0.4393

Max Act: 0.3250. Min Act: -0.0001

Data Index: 254481 (C4 (Web Text))

Max Activating Token Index: 924

Text #18

Max Range: 0.4393. Min Range: -0.4393

Max Act: 0.3237. Min Act: -0.0001

Data Index: 1108142 (C4 (Web Text))

Max Activating Token Index: 751

Text #19

Max Range: 0.4393. Min Range: -0.4393

Max Act: 0.3228. Min Act: -0.0000

Data Index: 606904 (C4 (Web Text))

Max Activating Token Index: 652