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

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

Neuron 3754 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: 0.6267. Min Range: -0.6267

Max Act: 0.6267. Min Act: -0.0000

Data Index: 913977 (C4 (Web Text))

Max Activating Token Index: 478

Text #1

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5296. Min Act: -0.0001

Data Index: 1086672 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.4854. Min Act: -0.0000

Data Index: 230193 (C4 (Web Text))

Max Activating Token Index: 314

Text #3

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.4578. Min Act: -0.0000

Data Index: 366585 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.4168. Min Act: -0.0000

Data Index: 620339 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.4124. Min Act: -0.0001

Data Index: 1072370 (C4 (Web Text))

Max Activating Token Index: 393

Text #6

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.4050. Min Act: -0.0001

Data Index: 1165938 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.4000. Min Act: -0.0001

Data Index: 1355521 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.3637. Min Act: -0.0001

Data Index: 771383 (C4 (Web Text))

Max Activating Token Index: 672

Text #9

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.3642. Min Act: -0.0000

Data Index: 754007 (C4 (Web Text))

Max Activating Token Index: 118

Text #10

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.3590. Min Act: -0.0000

Data Index: 247857 (C4 (Web Text))

Max Activating Token Index: 418

Text #11

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.3463. Min Act: -0.0000

Data Index: 441089 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.3292. Min Act: -0.0000

Data Index: 593363 (C4 (Web Text))

Max Activating Token Index: 834

Text #13

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.3380. Min Act: -0.0001

Data Index: 1140193 (C4 (Web Text))

Max Activating Token Index: 696

Text #14

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.3345. Min Act: -0.0001

Data Index: 248955 (C4 (Web Text))

Max Activating Token Index: 573

Text #15

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.3343. Min Act: -0.0000

Data Index: 914721 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.3451. Min Act: -0.0001

Data Index: 42661 (C4 (Web Text))

Max Activating Token Index: 673

Text #17

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.3324. Min Act: -0.0000

Data Index: 592149 (C4 (Web Text))

Max Activating Token Index: 883

Text #18

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.3232. Min Act: -0.0000

Data Index: 1344363 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.3332. Min Act: -0.0001

Data Index: 801720 (C4 (Web Text))

Max Activating Token Index: 886