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

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

Neuron 96 in Layer 0

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: 0.0231. Min Range: -0.0231

Max Act: 0.0231. Min Act: -0.0001

Data Index: 1497105 (Python Code)

Max Activating Token Index: 250

Text #1

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0228. Min Act: -0.0001

Data Index: 108027 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0227. Min Act: -0.0001

Data Index: 425558 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0226. Min Act: -0.0001

Data Index: 61810 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0225. Min Act: -0.0001

Data Index: 915784 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0224. Min Act: -0.0002

Data Index: 1463190 (Python Code)

Max Activating Token Index: 778

Text #6

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0220. Min Act: -0.0001

Data Index: 688576 (C4 (Web Text))

Max Activating Token Index: 555

Text #7

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0217. Min Act: -0.0001

Data Index: 848883 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0217. Min Act: -0.0001

Data Index: 166576 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0216. Min Act: -0.0001

Data Index: 38775 (C4 (Web Text))

Max Activating Token Index: 358

Text #10

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0218. Min Act: -0.0001

Data Index: 749423 (C4 (Web Text))

Max Activating Token Index: 288

Text #11

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0215. Min Act: -0.0001

Data Index: 1493435 (Python Code)

Max Activating Token Index: 460

Text #12

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0218. Min Act: -0.0001

Data Index: 695480 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0214. Min Act: -0.0001

Data Index: 1023404 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0214. Min Act: -0.0001

Data Index: 903818 (C4 (Web Text))

Max Activating Token Index: 241

Text #15

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0214. Min Act: -0.0001

Data Index: 613186 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0214. Min Act: -0.0001

Data Index: 861368 (C4 (Web Text))

Max Activating Token Index: 4

Text #17

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0214. Min Act: -0.0001

Data Index: 1044245 (C4 (Web Text))

Max Activating Token Index: 959

Text #18

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0212. Min Act: -0.0001

Data Index: 419678 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0215. Min Act: -0.0001

Data Index: 300177 (C4 (Web Text))

Max Activating Token Index: 340