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

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

Neuron 4540 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8151. Min Range: -0.8151

Max Act: 0.8111. Min Act: -0.0000

Data Index: 1276910 (C4 (Web Text))

Max Activating Token Index: 497

Text #1

Max Range: 0.8151. Min Range: -0.8151

Max Act: 0.8151. Min Act: -0.0000

Data Index: 948409 (C4 (Web Text))

Max Activating Token Index: 521

Text #2

Max Range: 0.8151. Min Range: -0.8151

Max Act: 0.6926. Min Act: -0.0000

Data Index: 826800 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 0.8151. Min Range: -0.8151

Max Act: 0.7163. Min Act: -0.0000

Data Index: 153346 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 0.8151. Min Range: -0.8151

Max Act: 0.6640. Min Act: -0.0000

Data Index: 1298257 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 0.8151. Min Range: -0.8151

Max Act: 0.6247. Min Act: -0.0000

Data Index: 1000652 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 0.8151. Min Range: -0.8151

Max Act: 0.6067. Min Act: -0.0000

Data Index: 388751 (C4 (Web Text))

Max Activating Token Index: 314

Text #7

Max Range: 0.8151. Min Range: -0.8151

Max Act: 0.6239. Min Act: -0.0000

Data Index: 1087945 (C4 (Web Text))

Max Activating Token Index: 792

Text #8

Max Range: 0.8151. Min Range: -0.8151

Max Act: 0.5555. Min Act: -0.0000

Data Index: 899585 (C4 (Web Text))

Max Activating Token Index: 84

Text #9

Max Range: 0.8151. Min Range: -0.8151

Max Act: 0.5745. Min Act: -0.0000

Data Index: 423330 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 0.8151. Min Range: -0.8151

Max Act: 0.5706. Min Act: -0.0000

Data Index: 469803 (C4 (Web Text))

Max Activating Token Index: 4

Text #11

Max Range: 0.8151. Min Range: -0.8151

Max Act: 0.5654. Min Act: -0.0000

Data Index: 120571 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 0.8151. Min Range: -0.8151

Max Act: 0.5626. Min Act: -0.0000

Data Index: 304576 (C4 (Web Text))

Max Activating Token Index: 457

Text #13

Max Range: 0.8151. Min Range: -0.8151

Max Act: 0.5602. Min Act: -0.0000

Data Index: 531826 (C4 (Web Text))

Max Activating Token Index: 284

Text #14

Max Range: 0.8151. Min Range: -0.8151

Max Act: 0.5388. Min Act: -0.0000

Data Index: 926152 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 0.8151. Min Range: -0.8151

Max Act: 0.5644. Min Act: -0.0000

Data Index: 967204 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 0.8151. Min Range: -0.8151

Max Act: 0.5446. Min Act: -0.0000

Data Index: 1147553 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 0.8151. Min Range: -0.8151

Max Act: 0.5389. Min Act: -0.0000

Data Index: 855392 (C4 (Web Text))

Max Activating Token Index: 555

Text #18

Max Range: 0.8151. Min Range: -0.8151

Max Act: 0.6110. Min Act: -0.0000

Data Index: 1172703 (C4 (Web Text))

Max Activating Token Index: 610

Text #19

Max Range: 0.8151. Min Range: -0.8151

Max Act: 0.5485. Min Act: -0.0000

Data Index: 533675 (C4 (Web Text))

Max Activating Token Index: 359