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

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

Neuron 723 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.3082. Min Act: -0.0000

Data Index: 633702 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2904. Min Act: -0.0000

Data Index: 1223373 (C4 (Web Text))

Max Activating Token Index: 847

Text #2

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.3016. Min Act: -0.0000

Data Index: 86801 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2679. Min Act: -0.0000

Data Index: 556762 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2666. Min Act: -0.0000

Data Index: 1163147 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2459. Min Act: -0.0001

Data Index: 1072078 (C4 (Web Text))

Max Activating Token Index: 798

Text #6

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2342. Min Act: -0.0001

Data Index: 803698 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2393. Min Act: -0.0000

Data Index: 598048 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2446. Min Act: -0.0000

Data Index: 923971 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2293. Min Act: -0.0001

Data Index: 408394 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2278. Min Act: -0.0000

Data Index: 396857 (C4 (Web Text))

Max Activating Token Index: 794

Text #11

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2346. Min Act: -0.0000

Data Index: 1309347 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2242. Min Act: -0.0000

Data Index: 912470 (C4 (Web Text))

Max Activating Token Index: 441

Text #13

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2240. Min Act: -0.0000

Data Index: 255464 (C4 (Web Text))

Max Activating Token Index: 737

Text #14

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2239. Min Act: -0.0001

Data Index: 1268888 (C4 (Web Text))

Max Activating Token Index: 918

Text #15

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2159. Min Act: -0.0000

Data Index: 424495 (C4 (Web Text))

Max Activating Token Index: 179

Text #16

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2154. Min Act: -0.0000

Data Index: 1340548 (C4 (Web Text))

Max Activating Token Index: 871

Text #17

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2213. Min Act: -0.0001

Data Index: 1277057 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2111. Min Act: -0.0000

Data Index: 1164270 (C4 (Web Text))

Max Activating Token Index: 215

Text #19

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2189. Min Act: -0.0001

Data Index: 724588 (C4 (Web Text))

Max Activating Token Index: 636