Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5979 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.7473. Min Act: -0.0000

Data Index: 1461371 (Python Code)

Max Activating Token Index: 159

Text #1

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.8026. Min Act: -0.0000

Data Index: 77218 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.7363. Min Act: -0.0000

Data Index: 601289 (C4 (Web Text))

Max Activating Token Index: 825

Text #3

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.7449. Min Act: -0.0000

Data Index: 52713 (C4 (Web Text))

Max Activating Token Index: 186

Text #4

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.7208. Min Act: -0.0000

Data Index: 94607 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.7050. Min Act: -0.0000

Data Index: 1581228 (Python Code)

Max Activating Token Index: 369

Text #6

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.6989. Min Act: -0.0000

Data Index: 725836 (C4 (Web Text))

Max Activating Token Index: 319

Text #7

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.6670. Min Act: -0.0000

Data Index: 1243560 (C4 (Web Text))

Max Activating Token Index: 476

Text #8

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.6269. Min Act: -0.0000

Data Index: 321789 (C4 (Web Text))

Max Activating Token Index: 300

Text #9

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.6246. Min Act: -0.0000

Data Index: 44285 (C4 (Web Text))

Max Activating Token Index: 983

Text #10

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.5979. Min Act: -0.0000

Data Index: 1088291 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.6601. Min Act: -0.0000

Data Index: 1381437 (Python Code)

Max Activating Token Index: 818

Text #12

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.4712. Min Act: -0.0000

Data Index: 192269 (C4 (Web Text))

Max Activating Token Index: 646

Text #13

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.5537. Min Act: -0.0000

Data Index: 711780 (C4 (Web Text))

Max Activating Token Index: 742

Text #14

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.5240. Min Act: -0.0000

Data Index: 22701 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.4862. Min Act: -0.0000

Data Index: 315919 (C4 (Web Text))

Max Activating Token Index: 272

Text #16

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.5282. Min Act: -0.0000

Data Index: 95043 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.4663. Min Act: -0.0000

Data Index: 73577 (C4 (Web Text))

Max Activating Token Index: 462

Text #18

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.4794. Min Act: -0.0000

Data Index: 1340193 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.5014. Min Act: -0.0000

Data Index: 1618252 (Python Code)

Max Activating Token Index: 668