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

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

Neuron 4172 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: 0.4474. Min Range: -0.4474

Max Act: 0.4474. Min Act: -0.0001

Data Index: 681061 (C4 (Web Text))

Max Activating Token Index: 762

Text #1

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3862. Min Act: -0.0001

Data Index: 915015 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3779. Min Act: -0.0001

Data Index: 500831 (C4 (Web Text))

Max Activating Token Index: 582

Text #3

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3698. Min Act: -0.0001

Data Index: 1139854 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3479. Min Act: -0.0001

Data Index: 1249110 (C4 (Web Text))

Max Activating Token Index: 777

Text #5

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3673. Min Act: -0.0001

Data Index: 28207 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3551. Min Act: -0.0001

Data Index: 1258740 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3415. Min Act: -0.0001

Data Index: 1251740 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3418. Min Act: -0.0001

Data Index: 934775 (C4 (Web Text))

Max Activating Token Index: 557

Text #9

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3619. Min Act: -0.0001

Data Index: 506604 (C4 (Web Text))

Max Activating Token Index: 319

Text #10

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3483. Min Act: -0.0000

Data Index: 905868 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3444. Min Act: -0.0000

Data Index: 1077905 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3434. Min Act: -0.0001

Data Index: 1345980 (C4 (Web Text))

Max Activating Token Index: 581

Text #13

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3503. Min Act: -0.0001

Data Index: 198367 (C4 (Web Text))

Max Activating Token Index: 350

Text #14

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3371. Min Act: -0.0001

Data Index: 581356 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3305. Min Act: -0.0001

Data Index: 390614 (C4 (Web Text))

Max Activating Token Index: 926

Text #16

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3725. Min Act: -0.0001

Data Index: 917213 (C4 (Web Text))

Max Activating Token Index: 866

Text #17

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3257. Min Act: -0.0001

Data Index: 896537 (C4 (Web Text))

Max Activating Token Index: 327

Text #18

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3189. Min Act: -0.0001

Data Index: 740796 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3070. Min Act: -0.0001

Data Index: 838784 (C4 (Web Text))

Max Activating Token Index: 55