Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 404 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0314. Min Act: -0.0003

Data Index: 1338976 (C4 (Web Text))

Max Activating Token Index: 382

Text #1

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0334. Min Act: -0.0003

Data Index: 652848 (C4 (Web Text))

Max Activating Token Index: 414

Text #2

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0310. Min Act: -0.0003

Data Index: 1166508 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0313. Min Act: -0.0003

Data Index: 471833 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0294. Min Act: -0.0003

Data Index: 638772 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0325. Min Act: -0.0003

Data Index: 1099615 (C4 (Web Text))

Max Activating Token Index: 186

Text #6

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0334. Min Act: -0.0003

Data Index: 951628 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0301. Min Act: -0.0003

Data Index: 478582 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0319. Min Act: -0.0003

Data Index: 1137866 (C4 (Web Text))

Max Activating Token Index: 247

Text #9

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0307. Min Act: -0.0003

Data Index: 1005015 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0320. Min Act: -0.0003

Data Index: 359262 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0307. Min Act: -0.0003

Data Index: 1000248 (C4 (Web Text))

Max Activating Token Index: 405

Text #12

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0276. Min Act: -0.0003

Data Index: 855430 (C4 (Web Text))

Max Activating Token Index: 688

Text #13

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0304. Min Act: -0.0003

Data Index: 635650 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0295. Min Act: -0.0003

Data Index: 322324 (C4 (Web Text))

Max Activating Token Index: 443

Text #15

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0312. Min Act: -0.0003

Data Index: 1077883 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0305. Min Act: -0.0003

Data Index: 322255 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0292. Min Act: -0.0003

Data Index: 465724 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0289. Min Act: -0.0003

Data Index: 1150603 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0284. Min Act: -0.0003

Data Index: 1350650 (C4 (Web Text))

Max Activating Token Index: 455