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

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

Neuron 1817 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: 1.8459. Min Range: -1.8459

Max Act: 1.8459. Min Act: -0.0001

Data Index: 97011 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 1.8459. Min Range: -1.8459

Max Act: 1.5652. Min Act: -0.0001

Data Index: 897521 (C4 (Web Text))

Max Activating Token Index: 608

Text #2

Max Range: 1.8459. Min Range: -1.8459

Max Act: 1.5652. Min Act: -0.0000

Data Index: 917529 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 1.8459. Min Range: -1.8459

Max Act: 1.5386. Min Act: -0.0000

Data Index: 358885 (C4 (Web Text))

Max Activating Token Index: 575

Text #4

Max Range: 1.8459. Min Range: -1.8459

Max Act: 1.4395. Min Act: -0.0000

Data Index: 1137622 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 1.8459. Min Range: -1.8459

Max Act: 1.3581. Min Act: -0.0000

Data Index: 573034 (C4 (Web Text))

Max Activating Token Index: 546

Text #6

Max Range: 1.8459. Min Range: -1.8459

Max Act: 1.4329. Min Act: -0.0000

Data Index: 618197 (C4 (Web Text))

Max Activating Token Index: 493

Text #7

Max Range: 1.8459. Min Range: -1.8459

Max Act: 1.3219. Min Act: -0.0001

Data Index: 1421212 (Python Code)

Max Activating Token Index: 125

Text #8

Max Range: 1.8459. Min Range: -1.8459

Max Act: 1.3666. Min Act: -0.0001

Data Index: 1560478 (Python Code)

Max Activating Token Index: 96

Text #9

Max Range: 1.8459. Min Range: -1.8459

Max Act: 1.3272. Min Act: -0.0001

Data Index: 771146 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 1.8459. Min Range: -1.8459

Max Act: 1.3286. Min Act: -0.0001

Data Index: 1400860 (Python Code)

Max Activating Token Index: 296

Text #11

Max Range: 1.8459. Min Range: -1.8459

Max Act: 1.2676. Min Act: -0.0001

Data Index: 13513 (C4 (Web Text))

Max Activating Token Index: 851

Text #12

Max Range: 1.8459. Min Range: -1.8459

Max Act: 1.3030. Min Act: -0.0000

Data Index: 1004888 (C4 (Web Text))

Max Activating Token Index: 676

Text #13

Max Range: 1.8459. Min Range: -1.8459

Max Act: 1.2666. Min Act: -0.0001

Data Index: 1641855 (Python Code)

Max Activating Token Index: 351

Text #14

Max Range: 1.8459. Min Range: -1.8459

Max Act: 1.4093. Min Act: -0.0000

Data Index: 966577 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 1.8459. Min Range: -1.8459

Max Act: 1.1773. Min Act: -0.0001

Data Index: 1534314 (Python Code)

Max Activating Token Index: 690

Text #16

Max Range: 1.8459. Min Range: -1.8459

Max Act: 1.3946. Min Act: -0.0000

Data Index: 1079757 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 1.8459. Min Range: -1.8459

Max Act: 1.2243. Min Act: -0.0001

Data Index: 1535295 (Python Code)

Max Activating Token Index: 153

Text #18

Max Range: 1.8459. Min Range: -1.8459

Max Act: 1.3565. Min Act: -0.0001

Data Index: 54009 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 1.8459. Min Range: -1.8459

Max Act: 1.1686. Min Act: -0.0000

Data Index: 1220221 (C4 (Web Text))

Max Activating Token Index: 202