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

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

Neuron 3483 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: 0.9606. Min Range: -0.9606

Max Act: 0.9470. Min Act: -0.0000

Data Index: 1290973 (C4 (Web Text))

Max Activating Token Index: 944

Text #1

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.9606. Min Act: -0.0000

Data Index: 771962 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.8445. Min Act: -0.0000

Data Index: 924968 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.8171. Min Act: -0.0000

Data Index: 490943 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.8268. Min Act: -0.0000

Data Index: 879617 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.7532. Min Act: -0.0000

Data Index: 946466 (C4 (Web Text))

Max Activating Token Index: 615

Text #6

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.7163. Min Act: -0.0000

Data Index: 197666 (C4 (Web Text))

Max Activating Token Index: 986

Text #7

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.7894. Min Act: -0.0000

Data Index: 448500 (C4 (Web Text))

Max Activating Token Index: 217

Text #8

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.7543. Min Act: -0.0000

Data Index: 730904 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.7225. Min Act: -0.0000

Data Index: 1043826 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.7065. Min Act: -0.0000

Data Index: 339904 (C4 (Web Text))

Max Activating Token Index: 812

Text #11

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.6238. Min Act: -0.0000

Data Index: 1334504 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.6434. Min Act: -0.0000

Data Index: 294403 (C4 (Web Text))

Max Activating Token Index: 277

Text #13

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.6476. Min Act: -0.0000

Data Index: 244050 (C4 (Web Text))

Max Activating Token Index: 731

Text #14

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.6429. Min Act: -0.0000

Data Index: 657175 (C4 (Web Text))

Max Activating Token Index: 619

Text #15

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.6154. Min Act: -0.0000

Data Index: 888431 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.5917. Min Act: -0.0000

Data Index: 237335 (C4 (Web Text))

Max Activating Token Index: 380

Text #17

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.6354. Min Act: -0.0000

Data Index: 402046 (C4 (Web Text))

Max Activating Token Index: 322

Text #18

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.6506. Min Act: -0.0000

Data Index: 815990 (C4 (Web Text))

Max Activating Token Index: 911

Text #19

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.6151. Min Act: -0.0000

Data Index: 68515 (C4 (Web Text))

Max Activating Token Index: 261