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

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

Neuron 5567 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2351. Min Range: -2.2351

Max Act: 2.0079. Min Act: -0.0000

Data Index: 406756 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 2.2351. Min Range: -2.2351

Max Act: 2.2351. Min Act: -0.0000

Data Index: 572835 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 2.2351. Min Range: -2.2351

Max Act: 2.1319. Min Act: -0.0000

Data Index: 1037480 (C4 (Web Text))

Max Activating Token Index: 585

Text #3

Max Range: 2.2351. Min Range: -2.2351

Max Act: 1.8060. Min Act: -0.0000

Data Index: 849672 (C4 (Web Text))

Max Activating Token Index: 220

Text #4

Max Range: 2.2351. Min Range: -2.2351

Max Act: 2.0022. Min Act: -0.0000

Data Index: 519341 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 2.2351. Min Range: -2.2351

Max Act: 1.7883. Min Act: -0.0000

Data Index: 930440 (C4 (Web Text))

Max Activating Token Index: 588

Text #6

Max Range: 2.2351. Min Range: -2.2351

Max Act: 1.9255. Min Act: -0.0001

Data Index: 324896 (C4 (Web Text))

Max Activating Token Index: 298

Text #7

Max Range: 2.2351. Min Range: -2.2351

Max Act: 1.8417. Min Act: -0.0000

Data Index: 165026 (C4 (Web Text))

Max Activating Token Index: 317

Text #8

Max Range: 2.2351. Min Range: -2.2351

Max Act: 1.8024. Min Act: -0.0000

Data Index: 871951 (C4 (Web Text))

Max Activating Token Index: 422

Text #9

Max Range: 2.2351. Min Range: -2.2351

Max Act: 1.7942. Min Act: -0.0000

Data Index: 60641 (C4 (Web Text))

Max Activating Token Index: 615

Text #10

Max Range: 2.2351. Min Range: -2.2351

Max Act: 1.6570. Min Act: -0.0000

Data Index: 110611 (C4 (Web Text))

Max Activating Token Index: 228

Text #11

Max Range: 2.2351. Min Range: -2.2351

Max Act: 1.6072. Min Act: -0.0000

Data Index: 206991 (C4 (Web Text))

Max Activating Token Index: 463

Text #12

Max Range: 2.2351. Min Range: -2.2351

Max Act: 1.7933. Min Act: -0.0000

Data Index: 1039588 (C4 (Web Text))

Max Activating Token Index: 186

Text #13

Max Range: 2.2351. Min Range: -2.2351

Max Act: 1.6988. Min Act: -0.0000

Data Index: 1271595 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 2.2351. Min Range: -2.2351

Max Act: 1.6519. Min Act: -0.0000

Data Index: 83903 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 2.2351. Min Range: -2.2351

Max Act: 1.7481. Min Act: -0.0000

Data Index: 745062 (C4 (Web Text))

Max Activating Token Index: 417

Text #16

Max Range: 2.2351. Min Range: -2.2351

Max Act: 1.6620. Min Act: -0.0000

Data Index: 534939 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 2.2351. Min Range: -2.2351

Max Act: 1.8298. Min Act: -0.0000

Data Index: 428364 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 2.2351. Min Range: -2.2351

Max Act: 1.5276. Min Act: -0.0000

Data Index: 1150764 (C4 (Web Text))

Max Activating Token Index: 887

Text #19

Max Range: 2.2351. Min Range: -2.2351

Max Act: 1.5887. Min Act: -0.0000

Data Index: 1093049 (C4 (Web Text))

Max Activating Token Index: 117