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

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

Neuron 5943 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1297. Min Range: -2.1297

Max Act: 2.1297. Min Act: -0.0000

Data Index: 744262 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 2.1297. Min Range: -2.1297

Max Act: 1.5388. Min Act: -0.0000

Data Index: 864607 (C4 (Web Text))

Max Activating Token Index: 954

Text #2

Max Range: 2.1297. Min Range: -2.1297

Max Act: 1.3385. Min Act: -0.0000

Data Index: 1358263 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 2.1297. Min Range: -2.1297

Max Act: 1.4384. Min Act: -0.0000

Data Index: 79813 (C4 (Web Text))

Max Activating Token Index: 590

Text #4

Max Range: 2.1297. Min Range: -2.1297

Max Act: 1.3557. Min Act: -0.0000

Data Index: 688832 (C4 (Web Text))

Max Activating Token Index: 525

Text #5

Max Range: 2.1297. Min Range: -2.1297

Max Act: 1.2733. Min Act: -0.0000

Data Index: 303563 (C4 (Web Text))

Max Activating Token Index: 422

Text #6

Max Range: 2.1297. Min Range: -2.1297

Max Act: 1.1871. Min Act: -0.0000

Data Index: 588931 (C4 (Web Text))

Max Activating Token Index: 479

Text #7

Max Range: 2.1297. Min Range: -2.1297

Max Act: 1.1931. Min Act: -0.0000

Data Index: 372748 (C4 (Web Text))

Max Activating Token Index: 194

Text #8

Max Range: 2.1297. Min Range: -2.1297

Max Act: 1.1230. Min Act: -0.0000

Data Index: 1071961 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 2.1297. Min Range: -2.1297

Max Act: 1.1134. Min Act: -0.0000

Data Index: 391282 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 2.1297. Min Range: -2.1297

Max Act: 1.0982. Min Act: -0.0000

Data Index: 401096 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 2.1297. Min Range: -2.1297

Max Act: 1.1060. Min Act: -0.0000

Data Index: 683380 (C4 (Web Text))

Max Activating Token Index: 1003

Text #12

Max Range: 2.1297. Min Range: -2.1297

Max Act: 1.1435. Min Act: -0.0000

Data Index: 247327 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 2.1297. Min Range: -2.1297

Max Act: 1.0713. Min Act: -0.0000

Data Index: 1082739 (C4 (Web Text))

Max Activating Token Index: 485

Text #14

Max Range: 2.1297. Min Range: -2.1297

Max Act: 1.0495. Min Act: -0.0000

Data Index: 791598 (C4 (Web Text))

Max Activating Token Index: 925

Text #15

Max Range: 2.1297. Min Range: -2.1297

Max Act: 0.9366. Min Act: -0.0000

Data Index: 981977 (C4 (Web Text))

Max Activating Token Index: 197

Text #16

Max Range: 2.1297. Min Range: -2.1297

Max Act: 1.0477. Min Act: -0.0000

Data Index: 241554 (C4 (Web Text))

Max Activating Token Index: 526

Text #17

Max Range: 2.1297. Min Range: -2.1297

Max Act: 0.9173. Min Act: -0.0000

Data Index: 1128113 (C4 (Web Text))

Max Activating Token Index: 674

Text #18

Max Range: 2.1297. Min Range: -2.1297

Max Act: 0.9700. Min Act: -0.0000

Data Index: 1224491 (C4 (Web Text))

Max Activating Token Index: 59

Text #19

Max Range: 2.1297. Min Range: -2.1297

Max Act: 0.9752. Min Act: -0.0000

Data Index: 331670 (C4 (Web Text))

Max Activating Token Index: 916