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

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

Neuron 3505 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.4282. Min Act: -0.0000

Data Index: 1264315 (C4 (Web Text))

Max Activating Token Index: 998

Text #1

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3603. Min Act: -0.0000

Data Index: 1288992 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3814. Min Act: -0.0001

Data Index: 1222607 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3918. Min Act: -0.0000

Data Index: 161222 (C4 (Web Text))

Max Activating Token Index: 907

Text #4

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3652. Min Act: -0.0000

Data Index: 542320 (C4 (Web Text))

Max Activating Token Index: 972

Text #5

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3599. Min Act: -0.0001

Data Index: 458217 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3749. Min Act: -0.0000

Data Index: 999119 (C4 (Web Text))

Max Activating Token Index: 123

Text #7

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3360. Min Act: -0.0000

Data Index: 160735 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3244. Min Act: -0.0000

Data Index: 1233909 (C4 (Web Text))

Max Activating Token Index: 272

Text #9

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3562. Min Act: -0.0001

Data Index: 760240 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3295. Min Act: -0.0001

Data Index: 617213 (C4 (Web Text))

Max Activating Token Index: 633

Text #11

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3269. Min Act: -0.0000

Data Index: 204821 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3241. Min Act: -0.0000

Data Index: 548200 (C4 (Web Text))

Max Activating Token Index: 172

Text #13

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3173. Min Act: -0.0000

Data Index: 1333855 (C4 (Web Text))

Max Activating Token Index: 417

Text #14

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3067. Min Act: -0.0000

Data Index: 1012491 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3162. Min Act: -0.0000

Data Index: 749965 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3150. Min Act: -0.0000

Data Index: 636091 (C4 (Web Text))

Max Activating Token Index: 343

Text #17

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3101. Min Act: -0.0000

Data Index: 84712 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3084. Min Act: -0.0000

Data Index: 176021 (C4 (Web Text))

Max Activating Token Index: 813

Text #19

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3072. Min Act: -0.0000

Data Index: 456971 (C4 (Web Text))

Max Activating Token Index: 200