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

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

Neuron 3428 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.9334. Min Range: -1.9334

Max Act: 1.9334. Min Act: -0.0001

Data Index: 236419 (C4 (Web Text))

Max Activating Token Index: 430

Text #1

Max Range: 1.9334. Min Range: -1.9334

Max Act: 1.7655. Min Act: -0.0001

Data Index: 233089 (C4 (Web Text))

Max Activating Token Index: 430

Text #2

Max Range: 1.9334. Min Range: -1.9334

Max Act: 1.7486. Min Act: -0.0001

Data Index: 1257337 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 1.9334. Min Range: -1.9334

Max Act: 1.4862. Min Act: -0.0001

Data Index: 1313136 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 1.9334. Min Range: -1.9334

Max Act: 1.6332. Min Act: -0.0001

Data Index: 522367 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 1.9334. Min Range: -1.9334

Max Act: 1.5633. Min Act: -0.0001

Data Index: 70281 (C4 (Web Text))

Max Activating Token Index: 170

Text #6

Max Range: 1.9334. Min Range: -1.9334

Max Act: 1.6628. Min Act: -0.0001

Data Index: 1258738 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 1.9334. Min Range: -1.9334

Max Act: 1.6546. Min Act: -0.0001

Data Index: 706444 (C4 (Web Text))

Max Activating Token Index: 254

Text #8

Max Range: 1.9334. Min Range: -1.9334

Max Act: 1.3680. Min Act: -0.0001

Data Index: 285695 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 1.9334. Min Range: -1.9334

Max Act: 1.6791. Min Act: -0.0001

Data Index: 97243 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 1.9334. Min Range: -1.9334

Max Act: 1.5802. Min Act: -0.0001

Data Index: 940384 (C4 (Web Text))

Max Activating Token Index: 549

Text #11

Max Range: 1.9334. Min Range: -1.9334

Max Act: 1.4853. Min Act: -0.0001

Data Index: 762433 (C4 (Web Text))

Max Activating Token Index: 312

Text #12

Max Range: 1.9334. Min Range: -1.9334

Max Act: 1.5820. Min Act: -0.0001

Data Index: 1210532 (C4 (Web Text))

Max Activating Token Index: 475

Text #13

Max Range: 1.9334. Min Range: -1.9334

Max Act: 1.4826. Min Act: -0.0001

Data Index: 349414 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 1.9334. Min Range: -1.9334

Max Act: 1.4234. Min Act: -0.0001

Data Index: 1213757 (C4 (Web Text))

Max Activating Token Index: 337

Text #15

Max Range: 1.9334. Min Range: -1.9334

Max Act: 1.8077. Min Act: -0.0001

Data Index: 733862 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 1.9334. Min Range: -1.9334

Max Act: 1.5854. Min Act: -0.0001

Data Index: 677941 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 1.9334. Min Range: -1.9334

Max Act: 1.7432. Min Act: -0.0001

Data Index: 542643 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 1.9334. Min Range: -1.9334

Max Act: 1.6908. Min Act: -0.0001

Data Index: 41910 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 1.9334. Min Range: -1.9334

Max Act: 1.5086. Min Act: -0.0001

Data Index: 1262733 (C4 (Web Text))

Max Activating Token Index: 45