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

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

Neuron 4486 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.4082. Min Range: -6.4082

Max Act: 6.4082. Min Act: -0.0000

Data Index: 745992 (C4 (Web Text))

Max Activating Token Index: 534

Text #1

Max Range: 6.4082. Min Range: -6.4082

Max Act: 6.1253. Min Act: -0.0000

Data Index: 523701 (C4 (Web Text))

Max Activating Token Index: 221

Text #2

Max Range: 6.4082. Min Range: -6.4082

Max Act: 5.7437. Min Act: -0.0000

Data Index: 9459 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 6.4082. Min Range: -6.4082

Max Act: 4.1224. Min Act: -0.0000

Data Index: 326166 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 6.4082. Min Range: -6.4082

Max Act: 4.2181. Min Act: -0.0000

Data Index: 434283 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 6.4082. Min Range: -6.4082

Max Act: 3.8738. Min Act: -0.0000

Data Index: 1006786 (C4 (Web Text))

Max Activating Token Index: 771

Text #6

Max Range: 6.4082. Min Range: -6.4082

Max Act: 4.1178. Min Act: -0.0000

Data Index: 461469 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 6.4082. Min Range: -6.4082

Max Act: 4.1382. Min Act: -0.0000

Data Index: 1325306 (C4 (Web Text))

Max Activating Token Index: 991

Text #8

Max Range: 6.4082. Min Range: -6.4082

Max Act: 3.7792. Min Act: -0.0000

Data Index: 796599 (C4 (Web Text))

Max Activating Token Index: 578

Text #9

Max Range: 6.4082. Min Range: -6.4082

Max Act: 3.8649. Min Act: -0.0000

Data Index: 618490 (C4 (Web Text))

Max Activating Token Index: 347

Text #10

Max Range: 6.4082. Min Range: -6.4082

Max Act: 3.7228. Min Act: -0.0000

Data Index: 1104014 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 6.4082. Min Range: -6.4082

Max Act: 3.7460. Min Act: -0.0000

Data Index: 495594 (C4 (Web Text))

Max Activating Token Index: 452

Text #12

Max Range: 6.4082. Min Range: -6.4082

Max Act: 3.7090. Min Act: -0.0000

Data Index: 820919 (C4 (Web Text))

Max Activating Token Index: 491

Text #13

Max Range: 6.4082. Min Range: -6.4082

Max Act: 3.6934. Min Act: -0.0000

Data Index: 335153 (C4 (Web Text))

Max Activating Token Index: 688

Text #14

Max Range: 6.4082. Min Range: -6.4082

Max Act: 3.4202. Min Act: -0.0000

Data Index: 1146285 (C4 (Web Text))

Max Activating Token Index: 729

Text #15

Max Range: 6.4082. Min Range: -6.4082

Max Act: 3.5338. Min Act: -0.0000

Data Index: 426115 (C4 (Web Text))

Max Activating Token Index: 917

Text #16

Max Range: 6.4082. Min Range: -6.4082

Max Act: 3.5295. Min Act: -0.0000

Data Index: 321031 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 6.4082. Min Range: -6.4082

Max Act: 3.3415. Min Act: -0.0000

Data Index: 1010922 (C4 (Web Text))

Max Activating Token Index: 192

Text #18

Max Range: 6.4082. Min Range: -6.4082

Max Act: 3.3438. Min Act: -0.0000

Data Index: 1095817 (C4 (Web Text))

Max Activating Token Index: 762

Text #19

Max Range: 6.4082. Min Range: -6.4082

Max Act: 3.3474. Min Act: -0.0000

Data Index: 527380 (C4 (Web Text))

Max Activating Token Index: 391