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

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

Neuron 3505 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: 0.9326. Min Range: -0.9326

Max Act: 0.9326. Min Act: -0.0000

Data Index: 1085259 (C4 (Web Text))

Max Activating Token Index: 245

Text #1

Max Range: 0.9326. Min Range: -0.9326

Max Act: 0.8403. Min Act: -0.0000

Data Index: 1347179 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 0.9326. Min Range: -0.9326

Max Act: 0.8046. Min Act: -0.0000

Data Index: 477463 (C4 (Web Text))

Max Activating Token Index: 425

Text #3

Max Range: 0.9326. Min Range: -0.9326

Max Act: 0.7996. Min Act: -0.0000

Data Index: 299570 (C4 (Web Text))

Max Activating Token Index: 103

Text #4

Max Range: 0.9326. Min Range: -0.9326

Max Act: 0.8409. Min Act: -0.0000

Data Index: 26207 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 0.9326. Min Range: -0.9326

Max Act: 0.7646. Min Act: -0.0000

Data Index: 568505 (C4 (Web Text))

Max Activating Token Index: 358

Text #6

Max Range: 0.9326. Min Range: -0.9326

Max Act: 0.7747. Min Act: -0.0000

Data Index: 182774 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 0.9326. Min Range: -0.9326

Max Act: 0.7527. Min Act: -0.0000

Data Index: 1074664 (C4 (Web Text))

Max Activating Token Index: 952

Text #8

Max Range: 0.9326. Min Range: -0.9326

Max Act: 0.7850. Min Act: -0.0000

Data Index: 816583 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 0.9326. Min Range: -0.9326

Max Act: 0.7844. Min Act: -0.0000

Data Index: 471120 (C4 (Web Text))

Max Activating Token Index: 111

Text #10

Max Range: 0.9326. Min Range: -0.9326

Max Act: 0.8206. Min Act: -0.0000

Data Index: 657906 (C4 (Web Text))

Max Activating Token Index: 456

Text #11

Max Range: 0.9326. Min Range: -0.9326

Max Act: 0.7971. Min Act: -0.0000

Data Index: 516973 (C4 (Web Text))

Max Activating Token Index: 212

Text #12

Max Range: 0.9326. Min Range: -0.9326

Max Act: 0.8228. Min Act: -0.0000

Data Index: 650765 (C4 (Web Text))

Max Activating Token Index: 949

Text #13

Max Range: 0.9326. Min Range: -0.9326

Max Act: 0.7909. Min Act: -0.0000

Data Index: 862393 (C4 (Web Text))

Max Activating Token Index: 400

Text #14

Max Range: 0.9326. Min Range: -0.9326

Max Act: 0.7239. Min Act: -0.0000

Data Index: 990499 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 0.9326. Min Range: -0.9326

Max Act: 0.8024. Min Act: -0.0000

Data Index: 748707 (C4 (Web Text))

Max Activating Token Index: 199

Text #16

Max Range: 0.9326. Min Range: -0.9326

Max Act: 0.7270. Min Act: -0.0000

Data Index: 1185865 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 0.9326. Min Range: -0.9326

Max Act: 0.7661. Min Act: -0.0000

Data Index: 675315 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 0.9326. Min Range: -0.9326

Max Act: 0.7156. Min Act: -0.0000

Data Index: 846447 (C4 (Web Text))

Max Activating Token Index: 341

Text #19

Max Range: 0.9326. Min Range: -0.9326

Max Act: 0.7913. Min Act: -0.0000

Data Index: 192690 (C4 (Web Text))

Max Activating Token Index: 907