Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 582 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4628. Min Range: -0.4628

Max Act: 0.4628. Min Act: -0.0001

Data Index: 1606740 (Python Code)

Max Activating Token Index: 334

Text #1

Max Range: 0.4628. Min Range: -0.4628

Max Act: 0.4445. Min Act: -0.0000

Data Index: 472689 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 0.4628. Min Range: -0.4628

Max Act: 0.4215. Min Act: -0.0001

Data Index: 66170 (C4 (Web Text))

Max Activating Token Index: 436

Text #3

Max Range: 0.4628. Min Range: -0.4628

Max Act: 0.4026. Min Act: -0.0001

Data Index: 813124 (C4 (Web Text))

Max Activating Token Index: 225

Text #4

Max Range: 0.4628. Min Range: -0.4628

Max Act: 0.3743. Min Act: -0.0001

Data Index: 750286 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 0.4628. Min Range: -0.4628

Max Act: 0.3258. Min Act: -0.0001

Data Index: 772929 (C4 (Web Text))

Max Activating Token Index: 655

Text #6

Max Range: 0.4628. Min Range: -0.4628

Max Act: 0.3608. Min Act: -0.0001

Data Index: 553809 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 0.4628. Min Range: -0.4628

Max Act: 0.3281. Min Act: -0.0000

Data Index: 1057238 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 0.4628. Min Range: -0.4628

Max Act: 0.3362. Min Act: -0.0001

Data Index: 392735 (C4 (Web Text))

Max Activating Token Index: 91

Text #9

Max Range: 0.4628. Min Range: -0.4628

Max Act: 0.3379. Min Act: -0.0001

Data Index: 490783 (C4 (Web Text))

Max Activating Token Index: 1011

Text #10

Max Range: 0.4628. Min Range: -0.4628

Max Act: 0.3366. Min Act: -0.0001

Data Index: 452151 (C4 (Web Text))

Max Activating Token Index: 491

Text #11

Max Range: 0.4628. Min Range: -0.4628

Max Act: 0.3399. Min Act: -0.0001

Data Index: 1110703 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 0.4628. Min Range: -0.4628

Max Act: 0.3204. Min Act: -0.0000

Data Index: 1211425 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 0.4628. Min Range: -0.4628

Max Act: 0.3196. Min Act: -0.0001

Data Index: 1252343 (C4 (Web Text))

Max Activating Token Index: 179

Text #14

Max Range: 0.4628. Min Range: -0.4628

Max Act: 0.3185. Min Act: -0.0001

Data Index: 567700 (C4 (Web Text))

Max Activating Token Index: 389

Text #15

Max Range: 0.4628. Min Range: -0.4628

Max Act: 0.3353. Min Act: -0.0001

Data Index: 990342 (C4 (Web Text))

Max Activating Token Index: 779

Text #16

Max Range: 0.4628. Min Range: -0.4628

Max Act: 0.3180. Min Act: -0.0000

Data Index: 756989 (C4 (Web Text))

Max Activating Token Index: 646

Text #17

Max Range: 0.4628. Min Range: -0.4628

Max Act: 0.3174. Min Act: -0.0001

Data Index: 851864 (C4 (Web Text))

Max Activating Token Index: 561

Text #18

Max Range: 0.4628. Min Range: -0.4628

Max Act: 0.3268. Min Act: -0.0001

Data Index: 1035576 (C4 (Web Text))

Max Activating Token Index: 709

Text #19

Max Range: 0.4628. Min Range: -0.4628

Max Act: 0.2889. Min Act: -0.0001

Data Index: 772747 (C4 (Web Text))

Max Activating Token Index: 580