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

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

Neuron 1574 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: 6.1071. Min Range: -6.1071

Max Act: 6.1071. Min Act: -0.0000

Data Index: 592623 (C4 (Web Text))

Max Activating Token Index: 530

Text #1

Max Range: 6.1071. Min Range: -6.1071

Max Act: 5.9718. Min Act: -0.0000

Data Index: 59131 (C4 (Web Text))

Max Activating Token Index: 896

Text #2

Max Range: 6.1071. Min Range: -6.1071

Max Act: 5.3097. Min Act: -0.0000

Data Index: 1300935 (C4 (Web Text))

Max Activating Token Index: 542

Text #3

Max Range: 6.1071. Min Range: -6.1071

Max Act: 5.2169. Min Act: -0.0000

Data Index: 851818 (C4 (Web Text))

Max Activating Token Index: 805

Text #4

Max Range: 6.1071. Min Range: -6.1071

Max Act: 5.3683. Min Act: -0.0000

Data Index: 405367 (C4 (Web Text))

Max Activating Token Index: 406

Text #5

Max Range: 6.1071. Min Range: -6.1071

Max Act: 5.3548. Min Act: -0.0000

Data Index: 57902 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 6.1071. Min Range: -6.1071

Max Act: 5.0704. Min Act: -0.0000

Data Index: 1009681 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 6.1071. Min Range: -6.1071

Max Act: 5.2510. Min Act: -0.0000

Data Index: 510557 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 6.1071. Min Range: -6.1071

Max Act: 5.2216. Min Act: -0.0000

Data Index: 785667 (C4 (Web Text))

Max Activating Token Index: 409

Text #9

Max Range: 6.1071. Min Range: -6.1071

Max Act: 5.1383. Min Act: -0.0000

Data Index: 644122 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 6.1071. Min Range: -6.1071

Max Act: 5.0728. Min Act: -0.0000

Data Index: 1007524 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 6.1071. Min Range: -6.1071

Max Act: 4.9963. Min Act: -0.0000

Data Index: 355481 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 6.1071. Min Range: -6.1071

Max Act: 4.8064. Min Act: -0.0000

Data Index: 854293 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 6.1071. Min Range: -6.1071

Max Act: 4.7556. Min Act: -0.0000

Data Index: 935006 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 6.1071. Min Range: -6.1071

Max Act: 4.6329. Min Act: -0.0000

Data Index: 776136 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 6.1071. Min Range: -6.1071

Max Act: 4.8123. Min Act: -0.0000

Data Index: 1018520 (C4 (Web Text))

Max Activating Token Index: 367

Text #16

Max Range: 6.1071. Min Range: -6.1071

Max Act: 4.5895. Min Act: -0.0000

Data Index: 900276 (C4 (Web Text))

Max Activating Token Index: 710

Text #17

Max Range: 6.1071. Min Range: -6.1071

Max Act: 4.6185. Min Act: -0.0000

Data Index: 617291 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 6.1071. Min Range: -6.1071

Max Act: 4.5072. Min Act: -0.0000

Data Index: 856514 (C4 (Web Text))

Max Activating Token Index: 492

Text #19

Max Range: 6.1071. Min Range: -6.1071

Max Act: 4.6756. Min Act: -0.0000

Data Index: 1000259 (C4 (Web Text))

Max Activating Token Index: 913