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

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

Neuron 1457 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4037. Min Range: -1.4037

Max Act: 1.2443. Min Act: 0.0000

Data Index: 1263895 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 1.4037. Min Range: -1.4037

Max Act: 1.4037. Min Act: -0.0000

Data Index: 1302841 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 1.4037. Min Range: -1.4037

Max Act: 1.1289. Min Act: -0.0000

Data Index: 748015 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 1.4037. Min Range: -1.4037

Max Act: 1.1317. Min Act: -0.0000

Data Index: 943192 (C4 (Web Text))

Max Activating Token Index: 907

Text #4

Max Range: 1.4037. Min Range: -1.4037

Max Act: 1.1263. Min Act: -0.0000

Data Index: 159862 (C4 (Web Text))

Max Activating Token Index: 722

Text #5

Max Range: 1.4037. Min Range: -1.4037

Max Act: 1.0972. Min Act: -0.0000

Data Index: 246039 (C4 (Web Text))

Max Activating Token Index: 880

Text #6

Max Range: 1.4037. Min Range: -1.4037

Max Act: 1.1005. Min Act: -0.0000

Data Index: 342202 (C4 (Web Text))

Max Activating Token Index: 361

Text #7

Max Range: 1.4037. Min Range: -1.4037

Max Act: 0.9545. Min Act: -0.0000

Data Index: 1126762 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 1.4037. Min Range: -1.4037

Max Act: 1.0396. Min Act: -0.0000

Data Index: 1199705 (C4 (Web Text))

Max Activating Token Index: 915

Text #9

Max Range: 1.4037. Min Range: -1.4037

Max Act: 1.0098. Min Act: -0.0000

Data Index: 1016461 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 1.4037. Min Range: -1.4037

Max Act: 0.9349. Min Act: -0.0000

Data Index: 469589 (C4 (Web Text))

Max Activating Token Index: 657

Text #11

Max Range: 1.4037. Min Range: -1.4037

Max Act: 0.9053. Min Act: -0.0000

Data Index: 857511 (C4 (Web Text))

Max Activating Token Index: 490

Text #12

Max Range: 1.4037. Min Range: -1.4037

Max Act: 0.8450. Min Act: -0.0000

Data Index: 311574 (C4 (Web Text))

Max Activating Token Index: 945

Text #13

Max Range: 1.4037. Min Range: -1.4037

Max Act: 0.8440. Min Act: -0.0000

Data Index: 726136 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 1.4037. Min Range: -1.4037

Max Act: 0.8413. Min Act: -0.0000

Data Index: 173485 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 1.4037. Min Range: -1.4037

Max Act: 0.9156. Min Act: -0.0000

Data Index: 346641 (C4 (Web Text))

Max Activating Token Index: 844

Text #16

Max Range: 1.4037. Min Range: -1.4037

Max Act: 0.8230. Min Act: -0.0000

Data Index: 519856 (C4 (Web Text))

Max Activating Token Index: 921

Text #17

Max Range: 1.4037. Min Range: -1.4037

Max Act: 0.9130. Min Act: -0.0000

Data Index: 175114 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 1.4037. Min Range: -1.4037

Max Act: 0.7878. Min Act: -0.0000

Data Index: 1143870 (C4 (Web Text))

Max Activating Token Index: 210

Text #19

Max Range: 1.4037. Min Range: -1.4037

Max Act: 0.7666. Min Act: -0.0000

Data Index: 266010 (C4 (Web Text))

Max Activating Token Index: 565