Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5516 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0394. Min Act: -0.0002

Data Index: 1232357 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0372. Min Act: -0.0002

Data Index: 545768 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0362. Min Act: -0.0002

Data Index: 266356 (C4 (Web Text))

Max Activating Token Index: 378

Text #3

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0360. Min Act: -0.0002

Data Index: 1069978 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0359. Min Act: -0.0002

Data Index: 1059567 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0362. Min Act: -0.0002

Data Index: 357984 (C4 (Web Text))

Max Activating Token Index: 45

Text #6

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0352. Min Act: -0.0002

Data Index: 1389942 (Python Code)

Max Activating Token Index: 799

Text #7

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0358. Min Act: -0.0002

Data Index: 1064888 (C4 (Web Text))

Max Activating Token Index: 158

Text #8

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0357. Min Act: -0.0002

Data Index: 379807 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0356. Min Act: -0.0002

Data Index: 685777 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0359. Min Act: -0.0002

Data Index: 475752 (C4 (Web Text))

Max Activating Token Index: 84

Text #11

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0355. Min Act: -0.0002

Data Index: 1015341 (C4 (Web Text))

Max Activating Token Index: 552

Text #12

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0359. Min Act: -0.0002

Data Index: 1009535 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0359. Min Act: -0.0002

Data Index: 1339651 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0353. Min Act: -0.0002

Data Index: 399261 (C4 (Web Text))

Max Activating Token Index: 135

Text #15

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0351. Min Act: -0.0002

Data Index: 1400295 (Python Code)

Max Activating Token Index: 632

Text #16

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0352. Min Act: -0.0002

Data Index: 521621 (C4 (Web Text))

Max Activating Token Index: 194

Text #17

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0339. Min Act: -0.0002

Data Index: 285488 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0337. Min Act: -0.0002

Data Index: 1405082 (Python Code)

Max Activating Token Index: 339

Text #19

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0334. Min Act: -0.0002

Data Index: 46297 (C4 (Web Text))

Max Activating Token Index: 78