Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3795 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0272. Min Act: -0.0003

Data Index: 1058280 (C4 (Web Text))

Max Activating Token Index: 1

Text #1

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0272. Min Act: -0.0003

Data Index: 139117 (C4 (Web Text))

Max Activating Token Index: 1

Text #2

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0272. Min Act: -0.0003

Data Index: 371873 (C4 (Web Text))

Max Activating Token Index: 1

Text #3

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0272. Min Act: -0.0003

Data Index: 1148534 (C4 (Web Text))

Max Activating Token Index: 1

Text #4

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0272. Min Act: -0.0003

Data Index: 393448 (C4 (Web Text))

Max Activating Token Index: 1

Text #5

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0272. Min Act: -0.0003

Data Index: 894470 (C4 (Web Text))

Max Activating Token Index: 1

Text #6

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0272. Min Act: -0.0003

Data Index: 1261855 (C4 (Web Text))

Max Activating Token Index: 1

Text #7

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0272. Min Act: -0.0003

Data Index: 1209869 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0268. Min Act: -0.0003

Data Index: 418800 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0264. Min Act: -0.0003

Data Index: 504980 (C4 (Web Text))

Max Activating Token Index: 108

Text #10

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0263. Min Act: -0.0003

Data Index: 1297321 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0263. Min Act: -0.0003

Data Index: 632576 (C4 (Web Text))

Max Activating Token Index: 543

Text #12

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0262. Min Act: -0.0003

Data Index: 582804 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0261. Min Act: -0.0003

Data Index: 827575 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0261. Min Act: -0.0003

Data Index: 616970 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0260. Min Act: -0.0003

Data Index: 182193 (C4 (Web Text))

Max Activating Token Index: 174

Text #16

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0260. Min Act: -0.0003

Data Index: 197603 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0259. Min Act: -0.0003

Data Index: 820938 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0259. Min Act: -0.0003

Data Index: 513146 (C4 (Web Text))

Max Activating Token Index: 264

Text #19

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0258. Min Act: -0.0003

Data Index: 729382 (C4 (Web Text))

Max Activating Token Index: 104