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

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

Neuron 1597 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.6151. Min Range: -6.6151

Max Act: 6.6151. Min Act: -0.0000

Data Index: 730655 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 6.6151. Min Range: -6.6151

Max Act: 6.1432. Min Act: -0.0000

Data Index: 875279 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 6.6151. Min Range: -6.6151

Max Act: 6.2195. Min Act: -0.0000

Data Index: 896054 (C4 (Web Text))

Max Activating Token Index: 334

Text #3

Max Range: 6.6151. Min Range: -6.6151

Max Act: 6.1936. Min Act: -0.0000

Data Index: 280542 (C4 (Web Text))

Max Activating Token Index: 209

Text #4

Max Range: 6.6151. Min Range: -6.6151

Max Act: 5.7333. Min Act: -0.0000

Data Index: 342704 (C4 (Web Text))

Max Activating Token Index: 563

Text #5

Max Range: 6.6151. Min Range: -6.6151

Max Act: 5.8875. Min Act: -0.0000

Data Index: 363681 (C4 (Web Text))

Max Activating Token Index: 502

Text #6

Max Range: 6.6151. Min Range: -6.6151

Max Act: 5.4817. Min Act: -0.0000

Data Index: 52668 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 6.6151. Min Range: -6.6151

Max Act: 5.7161. Min Act: -0.0000

Data Index: 949343 (C4 (Web Text))

Max Activating Token Index: 238

Text #8

Max Range: 6.6151. Min Range: -6.6151

Max Act: 5.5358. Min Act: -0.0000

Data Index: 1018823 (C4 (Web Text))

Max Activating Token Index: 626

Text #9

Max Range: 6.6151. Min Range: -6.6151

Max Act: 5.2879. Min Act: -0.0000

Data Index: 525156 (C4 (Web Text))

Max Activating Token Index: 631

Text #10

Max Range: 6.6151. Min Range: -6.6151

Max Act: 5.6697. Min Act: -0.0000

Data Index: 950305 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 6.6151. Min Range: -6.6151

Max Act: 5.6463. Min Act: -0.0000

Data Index: 759040 (C4 (Web Text))

Max Activating Token Index: 621

Text #12

Max Range: 6.6151. Min Range: -6.6151

Max Act: 5.6027. Min Act: -0.0000

Data Index: 634598 (C4 (Web Text))

Max Activating Token Index: 652

Text #13

Max Range: 6.6151. Min Range: -6.6151

Max Act: 5.3113. Min Act: -0.0000

Data Index: 837065 (C4 (Web Text))

Max Activating Token Index: 842

Text #14

Max Range: 6.6151. Min Range: -6.6151

Max Act: 5.2345. Min Act: -0.0000

Data Index: 287001 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 6.6151. Min Range: -6.6151

Max Act: 5.2063. Min Act: -0.0000

Data Index: 397153 (C4 (Web Text))

Max Activating Token Index: 114

Text #16

Max Range: 6.6151. Min Range: -6.6151

Max Act: 5.5764. Min Act: -0.0000

Data Index: 276559 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 6.6151. Min Range: -6.6151

Max Act: 5.1209. Min Act: -0.0000

Data Index: 744598 (C4 (Web Text))

Max Activating Token Index: 689

Text #18

Max Range: 6.6151. Min Range: -6.6151

Max Act: 5.1069. Min Act: -0.0000

Data Index: 764664 (C4 (Web Text))

Max Activating Token Index: 867

Text #19

Max Range: 6.6151. Min Range: -6.6151

Max Act: 5.1042. Min Act: -0.0000

Data Index: 1258295 (C4 (Web Text))

Max Activating Token Index: 148