Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1005 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0394. Min Act: -0.0003

Data Index: 710036 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0392. Min Act: -0.0003

Data Index: 751936 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0328. Min Act: -0.0003

Data Index: 1290663 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0349. Min Act: -0.0003

Data Index: 1070008 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0292. Min Act: -0.0003

Data Index: 571235 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0273. Min Act: -0.0003

Data Index: 53563 (C4 (Web Text))

Max Activating Token Index: 372

Text #6

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0298. Min Act: -0.0003

Data Index: 1248198 (C4 (Web Text))

Max Activating Token Index: 455

Text #7

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0273. Min Act: -0.0003

Data Index: 947034 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0273. Min Act: -0.0003

Data Index: 745536 (C4 (Web Text))

Max Activating Token Index: 889

Text #9

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0300. Min Act: -0.0003

Data Index: 964823 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0290. Min Act: -0.0003

Data Index: 814973 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0259. Min Act: -0.0003

Data Index: 453510 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0285. Min Act: -0.0003

Data Index: 958114 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0286. Min Act: -0.0003

Data Index: 811801 (C4 (Web Text))

Max Activating Token Index: 196

Text #14

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0280. Min Act: -0.0003

Data Index: 397845 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0267. Min Act: -0.0003

Data Index: 1304629 (C4 (Web Text))

Max Activating Token Index: 474

Text #16

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0270. Min Act: -0.0003

Data Index: 735762 (C4 (Web Text))

Max Activating Token Index: 413

Text #17

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0268. Min Act: -0.0003

Data Index: 959075 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0269. Min Act: -0.0003

Data Index: 1317844 (C4 (Web Text))

Max Activating Token Index: 217

Text #19

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0256. Min Act: -0.0003

Data Index: 1567730 (Python Code)

Max Activating Token Index: 371