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

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

Neuron 3804 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0405. Min Act: -0.0003

Data Index: 1186585 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0374. Min Act: -0.0003

Data Index: 1077614 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0366. Min Act: -0.0003

Data Index: 588591 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0371. Min Act: -0.0003

Data Index: 710253 (C4 (Web Text))

Max Activating Token Index: 643

Text #4

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0350. Min Act: -0.0003

Data Index: 331012 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0355. Min Act: -0.0003

Data Index: 1298799 (C4 (Web Text))

Max Activating Token Index: 56

Text #6

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0346. Min Act: -0.0002

Data Index: 442462 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0340. Min Act: -0.0003

Data Index: 1216165 (C4 (Web Text))

Max Activating Token Index: 292

Text #8

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0335. Min Act: -0.0003

Data Index: 831526 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0327. Min Act: -0.0003

Data Index: 895603 (C4 (Web Text))

Max Activating Token Index: 447

Text #10

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0316. Min Act: -0.0003

Data Index: 1157240 (C4 (Web Text))

Max Activating Token Index: 925

Text #11

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0321. Min Act: -0.0002

Data Index: 1252995 (C4 (Web Text))

Max Activating Token Index: 570

Text #12

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0332. Min Act: -0.0003

Data Index: 156892 (C4 (Web Text))

Max Activating Token Index: 649

Text #13

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0333. Min Act: -0.0002

Data Index: 268018 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0324. Min Act: -0.0003

Data Index: 853753 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0317. Min Act: -0.0003

Data Index: 1042784 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0314. Min Act: -0.0003

Data Index: 1286354 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0312. Min Act: -0.0003

Data Index: 664625 (C4 (Web Text))

Max Activating Token Index: 77

Text #18

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0315. Min Act: -0.0003

Data Index: 1156233 (C4 (Web Text))

Max Activating Token Index: 537

Text #19

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0313. Min Act: -0.0003

Data Index: 731276 (C4 (Web Text))

Max Activating Token Index: 132