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

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

Neuron 1051 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0295. Min Act: -0.0004

Data Index: 1394220 (Python Code)

Max Activating Token Index: 731

Text #1

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0292. Min Act: -0.0004

Data Index: 1391929 (Python Code)

Max Activating Token Index: 116

Text #2

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0291. Min Act: -0.0004

Data Index: 1587541 (Python Code)

Max Activating Token Index: 642

Text #3

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0272. Min Act: -0.0004

Data Index: 156685 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0276. Min Act: -0.0004

Data Index: 270947 (C4 (Web Text))

Max Activating Token Index: 975

Text #5

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0280. Min Act: -0.0004

Data Index: 808909 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0258. Min Act: -0.0004

Data Index: 80162 (C4 (Web Text))

Max Activating Token Index: 800

Text #7

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0280. Min Act: -0.0004

Data Index: 707071 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0267. Min Act: -0.0004

Data Index: 997922 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0255. Min Act: -0.0004

Data Index: 1581943 (Python Code)

Max Activating Token Index: 6

Text #10

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0270. Min Act: -0.0004

Data Index: 11464 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0258. Min Act: -0.0004

Data Index: 1424509 (Python Code)

Max Activating Token Index: 496

Text #12

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0286. Min Act: -0.0004

Data Index: 1408189 (Python Code)

Max Activating Token Index: 502

Text #13

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0269. Min Act: -0.0004

Data Index: 1567255 (Python Code)

Max Activating Token Index: 979

Text #14

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0257. Min Act: -0.0004

Data Index: 1423286 (Python Code)

Max Activating Token Index: 44

Text #15

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0259. Min Act: -0.0004

Data Index: 444785 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0260. Min Act: -0.0004

Data Index: 919405 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0254. Min Act: -0.0004

Data Index: 1102447 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0229. Min Act: -0.0004

Data Index: 1468598 (Python Code)

Max Activating Token Index: 746

Text #19

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0253. Min Act: -0.0004

Data Index: 558399 (C4 (Web Text))

Max Activating Token Index: 460