Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1813 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1319. Min Act: -0.0000

Data Index: 868211 (C4 (Web Text))

Max Activating Token Index: 610

Text #1

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1207. Min Act: -0.0000

Data Index: 588760 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1039. Min Act: -0.0000

Data Index: 118258 (C4 (Web Text))

Max Activating Token Index: 396

Text #3

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1002. Min Act: 0.0000

Data Index: 1113140 (C4 (Web Text))

Max Activating Token Index: 483

Text #4

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1072. Min Act: 0.0000

Data Index: 146456 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1014. Min Act: -0.0000

Data Index: 1340370 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1054. Min Act: -0.0000

Data Index: 367193 (C4 (Web Text))

Max Activating Token Index: 516

Text #7

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.0979. Min Act: -0.0000

Data Index: 248904 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1014. Min Act: -0.0000

Data Index: 484683 (C4 (Web Text))

Max Activating Token Index: 336

Text #9

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.0944. Min Act: -0.0000

Data Index: 310022 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.0976. Min Act: -0.0000

Data Index: 1084681 (C4 (Web Text))

Max Activating Token Index: 583

Text #11

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.0844. Min Act: -0.0000

Data Index: 1010556 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.0896. Min Act: -0.0000

Data Index: 1298892 (C4 (Web Text))

Max Activating Token Index: 544

Text #13

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.0898. Min Act: -0.0000

Data Index: 607549 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.0844. Min Act: -0.0000

Data Index: 177142 (C4 (Web Text))

Max Activating Token Index: 336

Text #15

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.0866. Min Act: 0.0000

Data Index: 738488 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.0999. Min Act: -0.0000

Data Index: 882560 (C4 (Web Text))

Max Activating Token Index: 899

Text #17

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.0925. Min Act: -0.0000

Data Index: 860053 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.0864. Min Act: -0.0000

Data Index: 477106 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.0903. Min Act: -0.0000

Data Index: 771451 (C4 (Web Text))

Max Activating Token Index: 588