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

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

Neuron 3712 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4541. Min Range: -1.4541

Max Act: 1.4541. Min Act: -0.0000

Data Index: 198672 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 1.4541. Min Range: -1.4541

Max Act: 1.0158. Min Act: -0.0000

Data Index: 504570 (C4 (Web Text))

Max Activating Token Index: 57

Text #2

Max Range: 1.4541. Min Range: -1.4541

Max Act: 1.0593. Min Act: -0.0000

Data Index: 196014 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 1.4541. Min Range: -1.4541

Max Act: 1.0367. Min Act: -0.0000

Data Index: 1066441 (C4 (Web Text))

Max Activating Token Index: 338

Text #4

Max Range: 1.4541. Min Range: -1.4541

Max Act: 0.9505. Min Act: -0.0000

Data Index: 993265 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 1.4541. Min Range: -1.4541

Max Act: 0.9479. Min Act: -0.0000

Data Index: 590624 (C4 (Web Text))

Max Activating Token Index: 604

Text #6

Max Range: 1.4541. Min Range: -1.4541

Max Act: 0.8771. Min Act: -0.0000

Data Index: 978560 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 1.4541. Min Range: -1.4541

Max Act: 0.8037. Min Act: -0.0000

Data Index: 955991 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 1.4541. Min Range: -1.4541

Max Act: 0.8607. Min Act: -0.0000

Data Index: 652960 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 1.4541. Min Range: -1.4541

Max Act: 0.8526. Min Act: -0.0000

Data Index: 185786 (C4 (Web Text))

Max Activating Token Index: 111

Text #10

Max Range: 1.4541. Min Range: -1.4541

Max Act: 0.8777. Min Act: -0.0000

Data Index: 57370 (C4 (Web Text))

Max Activating Token Index: 555

Text #11

Max Range: 1.4541. Min Range: -1.4541

Max Act: 0.7971. Min Act: -0.0000

Data Index: 1269359 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 1.4541. Min Range: -1.4541

Max Act: 0.8278. Min Act: -0.0000

Data Index: 43535 (C4 (Web Text))

Max Activating Token Index: 912

Text #13

Max Range: 1.4541. Min Range: -1.4541

Max Act: 0.8189. Min Act: -0.0000

Data Index: 269327 (C4 (Web Text))

Max Activating Token Index: 176

Text #14

Max Range: 1.4541. Min Range: -1.4541

Max Act: 0.8065. Min Act: -0.0000

Data Index: 746334 (C4 (Web Text))

Max Activating Token Index: 1000

Text #15

Max Range: 1.4541. Min Range: -1.4541

Max Act: 0.7587. Min Act: -0.0000

Data Index: 452371 (C4 (Web Text))

Max Activating Token Index: 776

Text #16

Max Range: 1.4541. Min Range: -1.4541

Max Act: 0.7613. Min Act: -0.0000

Data Index: 977377 (C4 (Web Text))

Max Activating Token Index: 222

Text #17

Max Range: 1.4541. Min Range: -1.4541

Max Act: 0.7452. Min Act: -0.0000

Data Index: 441273 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 1.4541. Min Range: -1.4541

Max Act: 0.7305. Min Act: -0.0000

Data Index: 1264559 (C4 (Web Text))

Max Activating Token Index: 468

Text #19

Max Range: 1.4541. Min Range: -1.4541

Max Act: 0.7171. Min Act: -0.0000

Data Index: 1082746 (C4 (Web Text))

Max Activating Token Index: 394