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

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

Neuron 6073 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4399. Min Range: -2.4399

Max Act: 2.4399. Min Act: -0.0000

Data Index: 1164043 (C4 (Web Text))

Max Activating Token Index: 945

Text #1

Max Range: 2.4399. Min Range: -2.4399

Max Act: 2.0272. Min Act: -0.0000

Data Index: 771824 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 2.4399. Min Range: -2.4399

Max Act: 1.9098. Min Act: -0.0000

Data Index: 1251426 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 2.4399. Min Range: -2.4399

Max Act: 1.8303. Min Act: -0.0000

Data Index: 987504 (C4 (Web Text))

Max Activating Token Index: 917

Text #4

Max Range: 2.4399. Min Range: -2.4399

Max Act: 1.8394. Min Act: -0.0000

Data Index: 983929 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 2.4399. Min Range: -2.4399

Max Act: 1.7772. Min Act: -0.0000

Data Index: 74153 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 2.4399. Min Range: -2.4399

Max Act: 1.7340. Min Act: -0.0000

Data Index: 1072562 (C4 (Web Text))

Max Activating Token Index: 66

Text #7

Max Range: 2.4399. Min Range: -2.4399

Max Act: 1.7879. Min Act: -0.0000

Data Index: 313028 (C4 (Web Text))

Max Activating Token Index: 128

Text #8

Max Range: 2.4399. Min Range: -2.4399

Max Act: 1.7850. Min Act: -0.0000

Data Index: 81607 (C4 (Web Text))

Max Activating Token Index: 651

Text #9

Max Range: 2.4399. Min Range: -2.4399

Max Act: 1.7582. Min Act: -0.0000

Data Index: 771256 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 2.4399. Min Range: -2.4399

Max Act: 1.8157. Min Act: -0.0000

Data Index: 1029284 (C4 (Web Text))

Max Activating Token Index: 401

Text #11

Max Range: 2.4399. Min Range: -2.4399

Max Act: 1.6194. Min Act: -0.0000

Data Index: 816934 (C4 (Web Text))

Max Activating Token Index: 973

Text #12

Max Range: 2.4399. Min Range: -2.4399

Max Act: 1.7137. Min Act: -0.0000

Data Index: 1322744 (C4 (Web Text))

Max Activating Token Index: 739

Text #13

Max Range: 2.4399. Min Range: -2.4399

Max Act: 1.7159. Min Act: -0.0000

Data Index: 932800 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 2.4399. Min Range: -2.4399

Max Act: 1.5610. Min Act: -0.0000

Data Index: 787868 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 2.4399. Min Range: -2.4399

Max Act: 1.5715. Min Act: -0.0000

Data Index: 216800 (C4 (Web Text))

Max Activating Token Index: 331

Text #16

Max Range: 2.4399. Min Range: -2.4399

Max Act: 1.6481. Min Act: -0.0000

Data Index: 285824 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 2.4399. Min Range: -2.4399

Max Act: 1.6601. Min Act: -0.0000

Data Index: 894605 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 2.4399. Min Range: -2.4399

Max Act: 1.6638. Min Act: -0.0000

Data Index: 199733 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 2.4399. Min Range: -2.4399

Max Act: 1.5344. Min Act: -0.0000

Data Index: 848534 (C4 (Web Text))

Max Activating Token Index: 530