Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1747 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0250. Min Act: -0.0006

Data Index: 47030 (C4 (Web Text))

Max Activating Token Index: 170

Text #1

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0244. Min Act: -0.0006

Data Index: 281343 (C4 (Web Text))

Max Activating Token Index: 535

Text #2

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0235. Min Act: -0.0006

Data Index: 1204133 (C4 (Web Text))

Max Activating Token Index: 597

Text #3

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0235. Min Act: -0.0006

Data Index: 982413 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0234. Min Act: -0.0006

Data Index: 743165 (C4 (Web Text))

Max Activating Token Index: 701

Text #5

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0234. Min Act: -0.0006

Data Index: 509859 (C4 (Web Text))

Max Activating Token Index: 196

Text #6

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0233. Min Act: -0.0006

Data Index: 121972 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0232. Min Act: -0.0006

Data Index: 706498 (C4 (Web Text))

Max Activating Token Index: 597

Text #8

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0232. Min Act: -0.0006

Data Index: 1122583 (C4 (Web Text))

Max Activating Token Index: 673

Text #9

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0230. Min Act: -0.0006

Data Index: 1059917 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0230. Min Act: -0.0006

Data Index: 750469 (C4 (Web Text))

Max Activating Token Index: 612

Text #11

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0230. Min Act: -0.0006

Data Index: 957420 (C4 (Web Text))

Max Activating Token Index: 745

Text #12

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0230. Min Act: -0.0006

Data Index: 532649 (C4 (Web Text))

Max Activating Token Index: 71

Text #13

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0225. Min Act: -0.0006

Data Index: 450052 (C4 (Web Text))

Max Activating Token Index: 647

Text #14

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0225. Min Act: -0.0006

Data Index: 1243524 (C4 (Web Text))

Max Activating Token Index: 724

Text #15

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0230. Min Act: -0.0006

Data Index: 821527 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0230. Min Act: -0.0006

Data Index: 352393 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0235. Min Act: -0.0006

Data Index: 281550 (C4 (Web Text))

Max Activating Token Index: 622

Text #18

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0224. Min Act: -0.0006

Data Index: 1079823 (C4 (Web Text))

Max Activating Token Index: 690

Text #19

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0229. Min Act: -0.0006

Data Index: 811845 (C4 (Web Text))

Max Activating Token Index: 591