Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 27 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.4267. Min Act: -0.0003

Data Index: 1335785 (C4 (Web Text))

Max Activating Token Index: 463

Text #1

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.3734. Min Act: -0.0003

Data Index: 461904 (C4 (Web Text))

Max Activating Token Index: 410

Text #2

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.3424. Min Act: -0.0003

Data Index: 1318071 (C4 (Web Text))

Max Activating Token Index: 450

Text #3

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.3671. Min Act: -0.0003

Data Index: 920687 (C4 (Web Text))

Max Activating Token Index: 724

Text #4

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.3447. Min Act: -0.0003

Data Index: 571556 (C4 (Web Text))

Max Activating Token Index: 573

Text #5

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.3404. Min Act: -0.0003

Data Index: 121219 (C4 (Web Text))

Max Activating Token Index: 467

Text #6

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.3268. Min Act: -0.0003

Data Index: 1062465 (C4 (Web Text))

Max Activating Token Index: 266

Text #7

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.3262. Min Act: -0.0003

Data Index: 295796 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.3036. Min Act: -0.0003

Data Index: 290596 (C4 (Web Text))

Max Activating Token Index: 210

Text #9

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.3334. Min Act: -0.0003

Data Index: 473662 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.3297. Min Act: -0.0003

Data Index: 835440 (C4 (Web Text))

Max Activating Token Index: 202

Text #11

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.3180. Min Act: -0.0003

Data Index: 133309 (C4 (Web Text))

Max Activating Token Index: 831

Text #12

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.3154. Min Act: -0.0003

Data Index: 425385 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.3044. Min Act: -0.0003

Data Index: 585385 (C4 (Web Text))

Max Activating Token Index: 953

Text #14

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.3079. Min Act: -0.0003

Data Index: 1311074 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.2858. Min Act: -0.0003

Data Index: 51497 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.3076. Min Act: -0.0003

Data Index: 1037412 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.3037. Min Act: -0.0003

Data Index: 765279 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.2919. Min Act: -0.0003

Data Index: 134597 (C4 (Web Text))

Max Activating Token Index: 586

Text #19

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.2810. Min Act: -0.0003

Data Index: 1218912 (C4 (Web Text))

Max Activating Token Index: 71