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

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

Neuron 1858 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1814. Min Range: -2.1814

Max Act: 2.1814. Min Act: -0.0000

Data Index: 1115264 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 2.1814. Min Range: -2.1814

Max Act: 2.0292. Min Act: -0.0000

Data Index: 1090971 (C4 (Web Text))

Max Activating Token Index: 412

Text #2

Max Range: 2.1814. Min Range: -2.1814

Max Act: 2.1564. Min Act: -0.0000

Data Index: 223045 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 2.1814. Min Range: -2.1814

Max Act: 2.0032. Min Act: -0.0000

Data Index: 945696 (C4 (Web Text))

Max Activating Token Index: 934

Text #4

Max Range: 2.1814. Min Range: -2.1814

Max Act: 1.9297. Min Act: -0.0000

Data Index: 433112 (C4 (Web Text))

Max Activating Token Index: 542

Text #5

Max Range: 2.1814. Min Range: -2.1814

Max Act: 2.1538. Min Act: -0.0000

Data Index: 562457 (C4 (Web Text))

Max Activating Token Index: 477

Text #6

Max Range: 2.1814. Min Range: -2.1814

Max Act: 2.0090. Min Act: -0.0000

Data Index: 837848 (C4 (Web Text))

Max Activating Token Index: 907

Text #7

Max Range: 2.1814. Min Range: -2.1814

Max Act: 1.9053. Min Act: -0.0000

Data Index: 544046 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 2.1814. Min Range: -2.1814

Max Act: 1.3511. Min Act: -0.0000

Data Index: 683216 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 2.1814. Min Range: -2.1814

Max Act: 1.8879. Min Act: -0.0000

Data Index: 431410 (C4 (Web Text))

Max Activating Token Index: 603

Text #10

Max Range: 2.1814. Min Range: -2.1814

Max Act: 1.8710. Min Act: -0.0000

Data Index: 19897 (C4 (Web Text))

Max Activating Token Index: 117

Text #11

Max Range: 2.1814. Min Range: -2.1814

Max Act: 1.8331. Min Act: -0.0000

Data Index: 1124119 (C4 (Web Text))

Max Activating Token Index: 83

Text #12

Max Range: 2.1814. Min Range: -2.1814

Max Act: 1.8384. Min Act: -0.0000

Data Index: 948691 (C4 (Web Text))

Max Activating Token Index: 265

Text #13

Max Range: 2.1814. Min Range: -2.1814

Max Act: 1.8281. Min Act: -0.0000

Data Index: 644757 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 2.1814. Min Range: -2.1814

Max Act: 1.8153. Min Act: -0.0000

Data Index: 1136454 (C4 (Web Text))

Max Activating Token Index: 44

Text #15

Max Range: 2.1814. Min Range: -2.1814

Max Act: 1.5537. Min Act: -0.0000

Data Index: 466966 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 2.1814. Min Range: -2.1814

Max Act: 1.6584. Min Act: -0.0000

Data Index: 805287 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 2.1814. Min Range: -2.1814

Max Act: 1.6459. Min Act: -0.0000

Data Index: 446226 (C4 (Web Text))

Max Activating Token Index: 463

Text #18

Max Range: 2.1814. Min Range: -2.1814

Max Act: 1.7042. Min Act: -0.0000

Data Index: 1055967 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 2.1814. Min Range: -2.1814

Max Act: 1.6191. Min Act: -0.0000

Data Index: 32348 (C4 (Web Text))

Max Activating Token Index: 281