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

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

Neuron 338 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3840. Min Act: -0.0000

Data Index: 158896 (C4 (Web Text))

Max Activating Token Index: 861

Text #1

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3858. Min Act: -0.0000

Data Index: 159195 (C4 (Web Text))

Max Activating Token Index: 997

Text #2

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.4136. Min Act: -0.0000

Data Index: 1413181 (Python Code)

Max Activating Token Index: 672

Text #3

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3565. Min Act: -0.0000

Data Index: 186636 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3827. Min Act: -0.0000

Data Index: 448615 (C4 (Web Text))

Max Activating Token Index: 470

Text #5

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3523. Min Act: -0.0000

Data Index: 607335 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3474. Min Act: -0.0000

Data Index: 417169 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3315. Min Act: -0.0000

Data Index: 440382 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3527. Min Act: -0.0000

Data Index: 368131 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3389. Min Act: -0.0000

Data Index: 254617 (C4 (Web Text))

Max Activating Token Index: 415

Text #10

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3463. Min Act: -0.0000

Data Index: 1321361 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3302. Min Act: -0.0000

Data Index: 446592 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3305. Min Act: -0.0000

Data Index: 359211 (C4 (Web Text))

Max Activating Token Index: 502

Text #13

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3169. Min Act: -0.0000

Data Index: 232864 (C4 (Web Text))

Max Activating Token Index: 981

Text #14

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3189. Min Act: -0.0000

Data Index: 1485818 (Python Code)

Max Activating Token Index: 620

Text #15

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3055. Min Act: -0.0000

Data Index: 644747 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3453. Min Act: -0.0000

Data Index: 598181 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.2888. Min Act: -0.0000

Data Index: 449626 (C4 (Web Text))

Max Activating Token Index: 190

Text #18

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3414. Min Act: -0.0000

Data Index: 71946 (C4 (Web Text))

Max Activating Token Index: 713

Text #19

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.2955. Min Act: -0.0000

Data Index: 80468 (C4 (Web Text))

Max Activating Token Index: 360