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

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

Neuron 1627 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0470. Min Act: -0.0001

Data Index: 276653 (C4 (Web Text))

Max Activating Token Index: 601

Text #1

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0440. Min Act: -0.0001

Data Index: 714432 (C4 (Web Text))

Max Activating Token Index: 776

Text #2

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0450. Min Act: -0.0001

Data Index: 1038395 (C4 (Web Text))

Max Activating Token Index: 818

Text #3

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0422. Min Act: -0.0001

Data Index: 494541 (C4 (Web Text))

Max Activating Token Index: 587

Text #4

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0385. Min Act: -0.0001

Data Index: 1013469 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0387. Min Act: -0.0000

Data Index: 715313 (C4 (Web Text))

Max Activating Token Index: 524

Text #6

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0350. Min Act: -0.0001

Data Index: 757295 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0381. Min Act: -0.0000

Data Index: 1072608 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0325. Min Act: -0.0000

Data Index: 694897 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0300. Min Act: -0.0001

Data Index: 1574533 (Python Code)

Max Activating Token Index: 672

Text #10

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0281. Min Act: -0.0000

Data Index: 284049 (C4 (Web Text))

Max Activating Token Index: 480

Text #11

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0295. Min Act: -0.0000

Data Index: 4649 (C4 (Web Text))

Max Activating Token Index: 78

Text #12

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0258. Min Act: -0.0001

Data Index: 497253 (C4 (Web Text))

Max Activating Token Index: 741

Text #13

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0275. Min Act: -0.0001

Data Index: 28679 (C4 (Web Text))

Max Activating Token Index: 664

Text #14

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0259. Min Act: -0.0001

Data Index: 53211 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0260. Min Act: -0.0000

Data Index: 367218 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0259. Min Act: -0.0000

Data Index: 158637 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0254. Min Act: -0.0000

Data Index: 1133153 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0256. Min Act: -0.0000

Data Index: 325267 (C4 (Web Text))

Max Activating Token Index: 416

Text #19

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0261. Min Act: -0.0001

Data Index: 1034276 (C4 (Web Text))

Max Activating Token Index: 623