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

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

Neuron 3441 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: 0.5331. Min Range: -0.5331

Max Act: 0.5331. Min Act: -0.0000

Data Index: 683542 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.5083. Min Act: -0.0000

Data Index: 336730 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.4139. Min Act: -0.0000

Data Index: 1289703 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.4402. Min Act: -0.0000

Data Index: 640821 (C4 (Web Text))

Max Activating Token Index: 957

Text #4

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.4225. Min Act: -0.0000

Data Index: 292683 (C4 (Web Text))

Max Activating Token Index: 303

Text #5

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.3785. Min Act: -0.0000

Data Index: 282066 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.3715. Min Act: -0.0000

Data Index: 1358163 (C4 (Web Text))

Max Activating Token Index: 935

Text #7

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.3880. Min Act: -0.0000

Data Index: 1298845 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.4289. Min Act: -0.0000

Data Index: 1285961 (C4 (Web Text))

Max Activating Token Index: 70

Text #9

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.3701. Min Act: -0.0000

Data Index: 84507 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.3641. Min Act: -0.0000

Data Index: 730548 (C4 (Web Text))

Max Activating Token Index: 948

Text #11

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.3463. Min Act: -0.0000

Data Index: 1273508 (C4 (Web Text))

Max Activating Token Index: 639

Text #12

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.3281. Min Act: 0.0000

Data Index: 268221 (C4 (Web Text))

Max Activating Token Index: 711

Text #13

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.3185. Min Act: -0.0000

Data Index: 668581 (C4 (Web Text))

Max Activating Token Index: 530

Text #14

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.3248. Min Act: -0.0000

Data Index: 36203 (C4 (Web Text))

Max Activating Token Index: 798

Text #15

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.3470. Min Act: -0.0000

Data Index: 197839 (C4 (Web Text))

Max Activating Token Index: 616

Text #16

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.3211. Min Act: -0.0000

Data Index: 231943 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.3455. Min Act: -0.0000

Data Index: 44328 (C4 (Web Text))

Max Activating Token Index: 750

Text #18

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.3455. Min Act: -0.0000

Data Index: 231088 (C4 (Web Text))

Max Activating Token Index: 386

Text #19

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.2969. Min Act: 0.0000

Data Index: 1097487 (C4 (Web Text))

Max Activating Token Index: 906