Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2393 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.7260. Min Range: -1.7260

Max Act: 1.7260. Min Act: -0.0000

Data Index: 598843 (C4 (Web Text))

Max Activating Token Index: 314

Text #1

Max Range: 1.7260. Min Range: -1.7260

Max Act: 1.4645. Min Act: -0.0001

Data Index: 1398031 (Python Code)

Max Activating Token Index: 75

Text #2

Max Range: 1.7260. Min Range: -1.7260

Max Act: 1.2461. Min Act: -0.0001

Data Index: 588293 (C4 (Web Text))

Max Activating Token Index: 531

Text #3

Max Range: 1.7260. Min Range: -1.7260

Max Act: 1.1739. Min Act: 0.0000

Data Index: 1159087 (C4 (Web Text))

Max Activating Token Index: 1019

Text #4

Max Range: 1.7260. Min Range: -1.7260

Max Act: 1.1352. Min Act: -0.0000

Data Index: 1313078 (C4 (Web Text))

Max Activating Token Index: 943

Text #5

Max Range: 1.7260. Min Range: -1.7260

Max Act: 1.2072. Min Act: -0.0001

Data Index: 631989 (C4 (Web Text))

Max Activating Token Index: 947

Text #6

Max Range: 1.7260. Min Range: -1.7260

Max Act: 1.0166. Min Act: 0.0000

Data Index: 742324 (C4 (Web Text))

Max Activating Token Index: 115

Text #7

Max Range: 1.7260. Min Range: -1.7260

Max Act: 1.1085. Min Act: 0.0000

Data Index: 302181 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 1.7260. Min Range: -1.7260

Max Act: 1.0991. Min Act: -0.0001

Data Index: 983745 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 1.7260. Min Range: -1.7260

Max Act: 0.9118. Min Act: -0.0001

Data Index: 1374665 (Python Code)

Max Activating Token Index: 359

Text #10

Max Range: 1.7260. Min Range: -1.7260

Max Act: 0.9127. Min Act: -0.0000

Data Index: 1304616 (C4 (Web Text))

Max Activating Token Index: 710

Text #11

Max Range: 1.7260. Min Range: -1.7260

Max Act: 1.1256. Min Act: -0.0001

Data Index: 879704 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 1.7260. Min Range: -1.7260

Max Act: 1.0413. Min Act: -0.0001

Data Index: 920020 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 1.7260. Min Range: -1.7260

Max Act: 1.0986. Min Act: 0.0000

Data Index: 776114 (C4 (Web Text))

Max Activating Token Index: 364

Text #14

Max Range: 1.7260. Min Range: -1.7260

Max Act: 0.9964. Min Act: -0.0001

Data Index: 1368373 (Python Code)

Max Activating Token Index: 361

Text #15

Max Range: 1.7260. Min Range: -1.7260

Max Act: 1.0096. Min Act: -0.0000

Data Index: 210271 (C4 (Web Text))

Max Activating Token Index: 811

Text #16

Max Range: 1.7260. Min Range: -1.7260

Max Act: 0.9453. Min Act: -0.0000

Data Index: 178048 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 1.7260. Min Range: -1.7260

Max Act: 1.0409. Min Act: 0.0001

Data Index: 1200260 (C4 (Web Text))

Max Activating Token Index: 449

Text #18

Max Range: 1.7260. Min Range: -1.7260

Max Act: 0.8924. Min Act: -0.0000

Data Index: 408337 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 1.7260. Min Range: -1.7260

Max Act: 1.1198. Min Act: -0.0001

Data Index: 1539002 (Python Code)

Max Activating Token Index: 314