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

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

Neuron 6021 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: 2.8431. Min Range: -2.8431

Max Act: 2.8431. Min Act: -0.0000

Data Index: 1116537 (C4 (Web Text))

Max Activating Token Index: 850

Text #1

Max Range: 2.8431. Min Range: -2.8431

Max Act: 2.4708. Min Act: -0.0000

Data Index: 476169 (C4 (Web Text))

Max Activating Token Index: 615

Text #2

Max Range: 2.8431. Min Range: -2.8431

Max Act: 2.5310. Min Act: -0.0000

Data Index: 1132149 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 2.8431. Min Range: -2.8431

Max Act: 2.5389. Min Act: -0.0000

Data Index: 1178547 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 2.8431. Min Range: -2.8431

Max Act: 2.5337. Min Act: -0.0000

Data Index: 1350562 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 2.8431. Min Range: -2.8431

Max Act: 2.0541. Min Act: -0.0000

Data Index: 1410851 (Python Code)

Max Activating Token Index: 262

Text #6

Max Range: 2.8431. Min Range: -2.8431

Max Act: 2.1252. Min Act: -0.0000

Data Index: 1270938 (C4 (Web Text))

Max Activating Token Index: 949

Text #7

Max Range: 2.8431. Min Range: -2.8431

Max Act: 2.0692. Min Act: -0.0000

Data Index: 1278613 (C4 (Web Text))

Max Activating Token Index: 392

Text #8

Max Range: 2.8431. Min Range: -2.8431

Max Act: 1.9158. Min Act: -0.0000

Data Index: 780397 (C4 (Web Text))

Max Activating Token Index: 515

Text #9

Max Range: 2.8431. Min Range: -2.8431

Max Act: 1.8281. Min Act: -0.0000

Data Index: 398858 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 2.8431. Min Range: -2.8431

Max Act: 2.1339. Min Act: -0.0000

Data Index: 976589 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 2.8431. Min Range: -2.8431

Max Act: 2.1091. Min Act: -0.0000

Data Index: 1212087 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 2.8431. Min Range: -2.8431

Max Act: 1.9638. Min Act: -0.0000

Data Index: 999533 (C4 (Web Text))

Max Activating Token Index: 747

Text #13

Max Range: 2.8431. Min Range: -2.8431

Max Act: 2.0273. Min Act: -0.0000

Data Index: 907553 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 2.8431. Min Range: -2.8431

Max Act: 1.9039. Min Act: -0.0000

Data Index: 507048 (C4 (Web Text))

Max Activating Token Index: 988

Text #15

Max Range: 2.8431. Min Range: -2.8431

Max Act: 1.9972. Min Act: -0.0000

Data Index: 156470 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 2.8431. Min Range: -2.8431

Max Act: 1.7273. Min Act: 0.0000

Data Index: 280816 (C4 (Web Text))

Max Activating Token Index: 302

Text #17

Max Range: 2.8431. Min Range: -2.8431

Max Act: 1.9252. Min Act: -0.0000

Data Index: 250598 (C4 (Web Text))

Max Activating Token Index: 696

Text #18

Max Range: 2.8431. Min Range: -2.8431

Max Act: 1.8180. Min Act: -0.0000

Data Index: 746468 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 2.8431. Min Range: -2.8431

Max Act: 1.7889. Min Act: -0.0000

Data Index: 1129734 (C4 (Web Text))

Max Activating Token Index: 712