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

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

Neuron 3050 in Layer 2

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: 0.0384. Min Act: -0.0002

Data Index: 1319519 (C4 (Web Text))

Max Activating Token Index: 401

Text #1

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0385. Min Act: -0.0002

Data Index: 1191945 (C4 (Web Text))

Max Activating Token Index: 422

Text #2

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0369. Min Act: -0.0002

Data Index: 965302 (C4 (Web Text))

Max Activating Token Index: 875

Text #3

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0366. Min Act: -0.0002

Data Index: 451059 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0401. Min Act: -0.0002

Data Index: 59356 (C4 (Web Text))

Max Activating Token Index: 578

Text #5

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0357. Min Act: -0.0002

Data Index: 1338993 (C4 (Web Text))

Max Activating Token Index: 880

Text #6

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0326. Min Act: -0.0002

Data Index: 1238298 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0405. Min Act: -0.0002

Data Index: 600809 (C4 (Web Text))

Max Activating Token Index: 310

Text #8

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0352. Min Act: -0.0002

Data Index: 296017 (C4 (Web Text))

Max Activating Token Index: 315

Text #9

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0346. Min Act: -0.0002

Data Index: 155640 (C4 (Web Text))

Max Activating Token Index: 239

Text #10

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0354. Min Act: -0.0002

Data Index: 883437 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0361. Min Act: -0.0002

Data Index: 1280636 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0341. Min Act: -0.0002

Data Index: 479713 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0347. Min Act: -0.0002

Data Index: 111564 (C4 (Web Text))

Max Activating Token Index: 474

Text #14

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0315. Min Act: -0.0002

Data Index: 1313155 (C4 (Web Text))

Max Activating Token Index: 666

Text #15

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0349. Min Act: -0.0002

Data Index: 662419 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0321. Min Act: -0.0002

Data Index: 943327 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0324. Min Act: -0.0002

Data Index: 1166925 (C4 (Web Text))

Max Activating Token Index: 619

Text #18

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0351. Min Act: -0.0002

Data Index: 422056 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0348. Min Act: -0.0002

Data Index: 1038977 (C4 (Web Text))

Max Activating Token Index: 417