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

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

Neuron 3783 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6414. Min Range: -1.6414

Max Act: 1.6414. Min Act: -0.0000

Data Index: 1591551 (Python Code)

Max Activating Token Index: 672

Text #1

Max Range: 1.6414. Min Range: -1.6414

Max Act: 1.5152. Min Act: -0.0000

Data Index: 1465367 (Python Code)

Max Activating Token Index: 541

Text #2

Max Range: 1.6414. Min Range: -1.6414

Max Act: 1.3672. Min Act: -0.0000

Data Index: 1369288 (Python Code)

Max Activating Token Index: 150

Text #3

Max Range: 1.6414. Min Range: -1.6414

Max Act: 1.1499. Min Act: -0.0000

Data Index: 1128011 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 1.6414. Min Range: -1.6414

Max Act: 1.0723. Min Act: -0.0000

Data Index: 507015 (C4 (Web Text))

Max Activating Token Index: 416

Text #5

Max Range: 1.6414. Min Range: -1.6414

Max Act: 1.1078. Min Act: -0.0000

Data Index: 161023 (C4 (Web Text))

Max Activating Token Index: 225

Text #6

Max Range: 1.6414. Min Range: -1.6414

Max Act: 1.1210. Min Act: -0.0000

Data Index: 306532 (C4 (Web Text))

Max Activating Token Index: 111

Text #7

Max Range: 1.6414. Min Range: -1.6414

Max Act: 1.0955. Min Act: -0.0000

Data Index: 106531 (C4 (Web Text))

Max Activating Token Index: 268

Text #8

Max Range: 1.6414. Min Range: -1.6414

Max Act: 1.0801. Min Act: -0.0000

Data Index: 1281013 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 1.6414. Min Range: -1.6414

Max Act: 1.1176. Min Act: -0.0000

Data Index: 1315966 (C4 (Web Text))

Max Activating Token Index: 187

Text #10

Max Range: 1.6414. Min Range: -1.6414

Max Act: 1.0412. Min Act: -0.0000

Data Index: 1339061 (C4 (Web Text))

Max Activating Token Index: 694

Text #11

Max Range: 1.6414. Min Range: -1.6414

Max Act: 0.9362. Min Act: -0.0000

Data Index: 173323 (C4 (Web Text))

Max Activating Token Index: 617

Text #12

Max Range: 1.6414. Min Range: -1.6414

Max Act: 0.9737. Min Act: -0.0000

Data Index: 486493 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 1.6414. Min Range: -1.6414

Max Act: 0.8193. Min Act: -0.0000

Data Index: 432869 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 1.6414. Min Range: -1.6414

Max Act: 0.9334. Min Act: -0.0000

Data Index: 1156176 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 1.6414. Min Range: -1.6414

Max Act: 0.9525. Min Act: -0.0000

Data Index: 299896 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 1.6414. Min Range: -1.6414

Max Act: 1.0046. Min Act: -0.0000

Data Index: 289894 (C4 (Web Text))

Max Activating Token Index: 328

Text #17

Max Range: 1.6414. Min Range: -1.6414

Max Act: 0.8842. Min Act: -0.0000

Data Index: 1119373 (C4 (Web Text))

Max Activating Token Index: 442

Text #18

Max Range: 1.6414. Min Range: -1.6414

Max Act: 0.8813. Min Act: -0.0000

Data Index: 984974 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 1.6414. Min Range: -1.6414

Max Act: 0.8912. Min Act: -0.0000

Data Index: 829472 (C4 (Web Text))

Max Activating Token Index: 700