Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1773 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1169. Min Range: -1.1169

Max Act: 1.1169. Min Act: -0.0001

Data Index: 613915 (C4 (Web Text))

Max Activating Token Index: 397

Text #1

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.8062. Min Act: -0.0001

Data Index: 250403 (C4 (Web Text))

Max Activating Token Index: 956

Text #2

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.8044. Min Act: -0.0001

Data Index: 693436 (C4 (Web Text))

Max Activating Token Index: 170

Text #3

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.7202. Min Act: -0.0001

Data Index: 1289362 (C4 (Web Text))

Max Activating Token Index: 206

Text #4

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.7425. Min Act: -0.0001

Data Index: 1071479 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.7007. Min Act: -0.0001

Data Index: 729881 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.7449. Min Act: -0.0001

Data Index: 1083679 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.6767. Min Act: -0.0001

Data Index: 624635 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.7156. Min Act: -0.0001

Data Index: 757806 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.6838. Min Act: -0.0001

Data Index: 332361 (C4 (Web Text))

Max Activating Token Index: 193

Text #10

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.6609. Min Act: -0.0001

Data Index: 880397 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.6656. Min Act: -0.0001

Data Index: 398677 (C4 (Web Text))

Max Activating Token Index: 561

Text #12

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.6660. Min Act: -0.0001

Data Index: 492346 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.6242. Min Act: -0.0001

Data Index: 84498 (C4 (Web Text))

Max Activating Token Index: 268

Text #14

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.6649. Min Act: -0.0001

Data Index: 1223740 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.6239. Min Act: -0.0001

Data Index: 982159 (C4 (Web Text))

Max Activating Token Index: 120

Text #16

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.6211. Min Act: -0.0001

Data Index: 630265 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.6570. Min Act: -0.0001

Data Index: 712882 (C4 (Web Text))

Max Activating Token Index: 556

Text #18

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.6436. Min Act: -0.0001

Data Index: 534083 (C4 (Web Text))

Max Activating Token Index: 586

Text #19

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.6242. Min Act: -0.0001

Data Index: 906623 (C4 (Web Text))

Max Activating Token Index: 509