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

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

Neuron 1823 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4186. Min Range: -0.4186

Max Act: 0.4186. Min Act: -0.0000

Data Index: 584135 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 0.4186. Min Range: -0.4186

Max Act: 0.3905. Min Act: -0.0000

Data Index: 1279116 (C4 (Web Text))

Max Activating Token Index: 618

Text #2

Max Range: 0.4186. Min Range: -0.4186

Max Act: 0.3859. Min Act: -0.0000

Data Index: 918411 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 0.4186. Min Range: -0.4186

Max Act: 0.3529. Min Act: -0.0000

Data Index: 1276721 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 0.4186. Min Range: -0.4186

Max Act: 0.4027. Min Act: -0.0000

Data Index: 340686 (C4 (Web Text))

Max Activating Token Index: 666

Text #5

Max Range: 0.4186. Min Range: -0.4186

Max Act: 0.3533. Min Act: -0.0000

Data Index: 696538 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 0.4186. Min Range: -0.4186

Max Act: 0.3725. Min Act: -0.0000

Data Index: 400310 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 0.4186. Min Range: -0.4186

Max Act: 0.3452. Min Act: -0.0000

Data Index: 787306 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 0.4186. Min Range: -0.4186

Max Act: 0.3801. Min Act: -0.0000

Data Index: 803919 (C4 (Web Text))

Max Activating Token Index: 278

Text #9

Max Range: 0.4186. Min Range: -0.4186

Max Act: 0.3807. Min Act: -0.0000

Data Index: 1211784 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 0.4186. Min Range: -0.4186

Max Act: 0.3474. Min Act: -0.0000

Data Index: 514507 (C4 (Web Text))

Max Activating Token Index: 908

Text #11

Max Range: 0.4186. Min Range: -0.4186

Max Act: 0.3448. Min Act: -0.0000

Data Index: 804002 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 0.4186. Min Range: -0.4186

Max Act: 0.3584. Min Act: -0.0000

Data Index: 715878 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 0.4186. Min Range: -0.4186

Max Act: 0.3572. Min Act: -0.0000

Data Index: 636105 (C4 (Web Text))

Max Activating Token Index: 659

Text #14

Max Range: 0.4186. Min Range: -0.4186

Max Act: 0.3334. Min Act: -0.0000

Data Index: 58324 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 0.4186. Min Range: -0.4186

Max Act: 0.3436. Min Act: -0.0000

Data Index: 1055522 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 0.4186. Min Range: -0.4186

Max Act: 0.3434. Min Act: -0.0000

Data Index: 221338 (C4 (Web Text))

Max Activating Token Index: 429

Text #17

Max Range: 0.4186. Min Range: -0.4186

Max Act: 0.3309. Min Act: -0.0000

Data Index: 777687 (C4 (Web Text))

Max Activating Token Index: 57

Text #18

Max Range: 0.4186. Min Range: -0.4186

Max Act: 0.3421. Min Act: -0.0000

Data Index: 234472 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 0.4186. Min Range: -0.4186

Max Act: 0.3253. Min Act: -0.0000

Data Index: 407599 (C4 (Web Text))

Max Activating Token Index: 596