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

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

Neuron 1104 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0434. Min Act: -0.0002

Data Index: 170883 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0432. Min Act: -0.0002

Data Index: 724971 (C4 (Web Text))

Max Activating Token Index: 103

Text #2

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0376. Min Act: -0.0002

Data Index: 937284 (C4 (Web Text))

Max Activating Token Index: 510

Text #3

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0361. Min Act: -0.0002

Data Index: 790038 (C4 (Web Text))

Max Activating Token Index: 542

Text #4

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0358. Min Act: -0.0002

Data Index: 637225 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0341. Min Act: -0.0002

Data Index: 1176567 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0339. Min Act: -0.0002

Data Index: 968653 (C4 (Web Text))

Max Activating Token Index: 500

Text #7

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0331. Min Act: -0.0002

Data Index: 231170 (C4 (Web Text))

Max Activating Token Index: 409

Text #8

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0324. Min Act: -0.0002

Data Index: 3056 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0323. Min Act: -0.0002

Data Index: 1274392 (C4 (Web Text))

Max Activating Token Index: 319

Text #10

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0322. Min Act: -0.0002

Data Index: 755187 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0322. Min Act: -0.0002

Data Index: 1287178 (C4 (Web Text))

Max Activating Token Index: 86

Text #12

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0316. Min Act: -0.0002

Data Index: 13271 (C4 (Web Text))

Max Activating Token Index: 2

Text #13

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0320. Min Act: -0.0002

Data Index: 1163780 (C4 (Web Text))

Max Activating Token Index: 284

Text #14

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0320. Min Act: -0.0002

Data Index: 970563 (C4 (Web Text))

Max Activating Token Index: 934

Text #15

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0313. Min Act: -0.0002

Data Index: 1450026 (Python Code)

Max Activating Token Index: 111

Text #16

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0319. Min Act: -0.0002

Data Index: 1102073 (C4 (Web Text))

Max Activating Token Index: 955

Text #17

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0318. Min Act: -0.0002

Data Index: 514759 (C4 (Web Text))

Max Activating Token Index: 536

Text #18

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0316. Min Act: -0.0002

Data Index: 900895 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0314. Min Act: -0.0002

Data Index: 381274 (C4 (Web Text))

Max Activating Token Index: 811