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

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

Neuron 404 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: 1.5481. Min Range: -1.5481

Max Act: 1.5481. Min Act: -0.0000

Data Index: 284665 (C4 (Web Text))

Max Activating Token Index: 127

Text #1

Max Range: 1.5481. Min Range: -1.5481

Max Act: 1.2905. Min Act: -0.0000

Data Index: 917069 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 1.5481. Min Range: -1.5481

Max Act: 1.3436. Min Act: -0.0000

Data Index: 1009995 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 1.5481. Min Range: -1.5481

Max Act: 1.4109. Min Act: -0.0000

Data Index: 310785 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 1.5481. Min Range: -1.5481

Max Act: 1.1693. Min Act: -0.0000

Data Index: 472734 (C4 (Web Text))

Max Activating Token Index: 497

Text #5

Max Range: 1.5481. Min Range: -1.5481

Max Act: 1.2395. Min Act: -0.0000

Data Index: 1591826 (Python Code)

Max Activating Token Index: 117

Text #6

Max Range: 1.5481. Min Range: -1.5481

Max Act: 1.2224. Min Act: -0.0000

Data Index: 1332440 (C4 (Web Text))

Max Activating Token Index: 440

Text #7

Max Range: 1.5481. Min Range: -1.5481

Max Act: 1.2909. Min Act: -0.0000

Data Index: 554847 (C4 (Web Text))

Max Activating Token Index: 21

Text #8

Max Range: 1.5481. Min Range: -1.5481

Max Act: 1.2386. Min Act: -0.0000

Data Index: 802935 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 1.5481. Min Range: -1.5481

Max Act: 1.1730. Min Act: -0.0000

Data Index: 596901 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 1.5481. Min Range: -1.5481

Max Act: 1.2638. Min Act: -0.0000

Data Index: 1029014 (C4 (Web Text))

Max Activating Token Index: 390

Text #11

Max Range: 1.5481. Min Range: -1.5481

Max Act: 1.2136. Min Act: -0.0000

Data Index: 1642441 (Python Code)

Max Activating Token Index: 248

Text #12

Max Range: 1.5481. Min Range: -1.5481

Max Act: 1.2048. Min Act: -0.0000

Data Index: 1576737 (Python Code)

Max Activating Token Index: 889

Text #13

Max Range: 1.5481. Min Range: -1.5481

Max Act: 1.2241. Min Act: -0.0000

Data Index: 160823 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 1.5481. Min Range: -1.5481

Max Act: 1.2309. Min Act: -0.0000

Data Index: 813961 (C4 (Web Text))

Max Activating Token Index: 966

Text #15

Max Range: 1.5481. Min Range: -1.5481

Max Act: 1.1492. Min Act: -0.0000

Data Index: 234268 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 1.5481. Min Range: -1.5481

Max Act: 1.1402. Min Act: -0.0000

Data Index: 696605 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 1.5481. Min Range: -1.5481

Max Act: 1.1753. Min Act: -0.0000

Data Index: 1264663 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 1.5481. Min Range: -1.5481

Max Act: 1.1753. Min Act: -0.0000

Data Index: 378976 (C4 (Web Text))

Max Activating Token Index: 448

Text #19

Max Range: 1.5481. Min Range: -1.5481

Max Act: 1.1067. Min Act: -0.0000

Data Index: 1069919 (C4 (Web Text))

Max Activating Token Index: 108