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

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

Neuron 2024 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3908. Min Range: -1.3908

Max Act: 1.3908. Min Act: -0.0000

Data Index: 889190 (C4 (Web Text))

Max Activating Token Index: 805

Text #1

Max Range: 1.3908. Min Range: -1.3908

Max Act: 0.9206. Min Act: -0.0000

Data Index: 844431 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 1.3908. Min Range: -1.3908

Max Act: 0.8360. Min Act: -0.0000

Data Index: 561325 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 1.3908. Min Range: -1.3908

Max Act: 0.7911. Min Act: -0.0000

Data Index: 854640 (C4 (Web Text))

Max Activating Token Index: 553

Text #4

Max Range: 1.3908. Min Range: -1.3908

Max Act: 0.7704. Min Act: -0.0000

Data Index: 423790 (C4 (Web Text))

Max Activating Token Index: 438

Text #5

Max Range: 1.3908. Min Range: -1.3908

Max Act: 0.7592. Min Act: -0.0000

Data Index: 1216887 (C4 (Web Text))

Max Activating Token Index: 299

Text #6

Max Range: 1.3908. Min Range: -1.3908

Max Act: 0.7252. Min Act: -0.0000

Data Index: 525139 (C4 (Web Text))

Max Activating Token Index: 352

Text #7

Max Range: 1.3908. Min Range: -1.3908

Max Act: 0.7492. Min Act: -0.0000

Data Index: 375768 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 1.3908. Min Range: -1.3908

Max Act: 0.6597. Min Act: -0.0000

Data Index: 261034 (C4 (Web Text))

Max Activating Token Index: 145

Text #9

Max Range: 1.3908. Min Range: -1.3908

Max Act: 0.6296. Min Act: -0.0000

Data Index: 3571 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 1.3908. Min Range: -1.3908

Max Act: 0.6664. Min Act: -0.0000

Data Index: 267122 (C4 (Web Text))

Max Activating Token Index: 860

Text #11

Max Range: 1.3908. Min Range: -1.3908

Max Act: 0.6883. Min Act: -0.0000

Data Index: 230152 (C4 (Web Text))

Max Activating Token Index: 456

Text #12

Max Range: 1.3908. Min Range: -1.3908

Max Act: 0.6199. Min Act: -0.0000

Data Index: 380863 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 1.3908. Min Range: -1.3908

Max Act: 0.5797. Min Act: -0.0000

Data Index: 295961 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 1.3908. Min Range: -1.3908

Max Act: 0.5983. Min Act: -0.0000

Data Index: 269443 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 1.3908. Min Range: -1.3908

Max Act: 0.5759. Min Act: -0.0000

Data Index: 1224579 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 1.3908. Min Range: -1.3908

Max Act: 0.5359. Min Act: -0.0000

Data Index: 1079011 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 1.3908. Min Range: -1.3908

Max Act: 0.4863. Min Act: -0.0000

Data Index: 1044805 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 1.3908. Min Range: -1.3908

Max Act: 0.5270. Min Act: -0.0000

Data Index: 1222067 (C4 (Web Text))

Max Activating Token Index: 288

Text #19

Max Range: 1.3908. Min Range: -1.3908

Max Act: 0.4721. Min Act: -0.0000

Data Index: 1167750 (C4 (Web Text))

Max Activating Token Index: 68