Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 668 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0297. Min Act: -0.0006

Data Index: 427546 (C4 (Web Text))

Max Activating Token Index: 531

Text #1

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0294. Min Act: -0.0006

Data Index: 613450 (C4 (Web Text))

Max Activating Token Index: 964

Text #2

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0290. Min Act: -0.0006

Data Index: 658968 (C4 (Web Text))

Max Activating Token Index: 768

Text #3

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0286. Min Act: -0.0006

Data Index: 506720 (C4 (Web Text))

Max Activating Token Index: 260

Text #4

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0292. Min Act: -0.0006

Data Index: 841687 (C4 (Web Text))

Max Activating Token Index: 475

Text #5

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0281. Min Act: -0.0006

Data Index: 1329433 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0288. Min Act: -0.0006

Data Index: 3635 (C4 (Web Text))

Max Activating Token Index: 754

Text #7

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0265. Min Act: -0.0006

Data Index: 1007297 (C4 (Web Text))

Max Activating Token Index: 652

Text #8

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0283. Min Act: -0.0006

Data Index: 1400753 (Python Code)

Max Activating Token Index: 420

Text #9

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0271. Min Act: -0.0006

Data Index: 1351896 (C4 (Web Text))

Max Activating Token Index: 245

Text #10

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0269. Min Act: -0.0006

Data Index: 159283 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0269. Min Act: -0.0006

Data Index: 34162 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0273. Min Act: -0.0006

Data Index: 713723 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0271. Min Act: -0.0006

Data Index: 806274 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0270. Min Act: -0.0006

Data Index: 1272888 (C4 (Web Text))

Max Activating Token Index: 395

Text #15

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0264. Min Act: -0.0006

Data Index: 135602 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0263. Min Act: -0.0006

Data Index: 1648579 (Python Code)

Max Activating Token Index: 53

Text #17

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0274. Min Act: -0.0006

Data Index: 54396 (C4 (Web Text))

Max Activating Token Index: 719

Text #18

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0267. Min Act: -0.0006

Data Index: 815455 (C4 (Web Text))

Max Activating Token Index: 1009

Text #19

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0272. Min Act: -0.0006

Data Index: 177211 (C4 (Web Text))

Max Activating Token Index: 703