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

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

Neuron 6066 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: 5.3441. Min Range: -5.3441

Max Act: 4.9760. Min Act: -0.0000

Data Index: 626774 (C4 (Web Text))

Max Activating Token Index: 741

Text #1

Max Range: 5.3441. Min Range: -5.3441

Max Act: 5.1220. Min Act: -0.0000

Data Index: 35953 (C4 (Web Text))

Max Activating Token Index: 553

Text #2

Max Range: 5.3441. Min Range: -5.3441

Max Act: 5.3441. Min Act: -0.0000

Data Index: 784538 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 5.3441. Min Range: -5.3441

Max Act: 4.9528. Min Act: -0.0000

Data Index: 291220 (C4 (Web Text))

Max Activating Token Index: 394

Text #4

Max Range: 5.3441. Min Range: -5.3441

Max Act: 4.5565. Min Act: -0.0000

Data Index: 1265829 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 5.3441. Min Range: -5.3441

Max Act: 4.5242. Min Act: -0.0000

Data Index: 479972 (C4 (Web Text))

Max Activating Token Index: 73

Text #6

Max Range: 5.3441. Min Range: -5.3441

Max Act: 4.5076. Min Act: -0.0000

Data Index: 682119 (C4 (Web Text))

Max Activating Token Index: 576

Text #7

Max Range: 5.3441. Min Range: -5.3441

Max Act: 4.6779. Min Act: -0.0000

Data Index: 219291 (C4 (Web Text))

Max Activating Token Index: 549

Text #8

Max Range: 5.3441. Min Range: -5.3441

Max Act: 4.4851. Min Act: -0.0000

Data Index: 1168279 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 5.3441. Min Range: -5.3441

Max Act: 4.6265. Min Act: -0.0000

Data Index: 165982 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 5.3441. Min Range: -5.3441

Max Act: 4.7833. Min Act: -0.0000

Data Index: 768685 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 5.3441. Min Range: -5.3441

Max Act: 4.6183. Min Act: -0.0000

Data Index: 17585 (C4 (Web Text))

Max Activating Token Index: 627

Text #12

Max Range: 5.3441. Min Range: -5.3441

Max Act: 4.7601. Min Act: -0.0000

Data Index: 31123 (C4 (Web Text))

Max Activating Token Index: 925

Text #13

Max Range: 5.3441. Min Range: -5.3441

Max Act: 4.2968. Min Act: -0.0000

Data Index: 138628 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 5.3441. Min Range: -5.3441

Max Act: 4.6459. Min Act: -0.0000

Data Index: 1018932 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 5.3441. Min Range: -5.3441

Max Act: 4.3017. Min Act: -0.0000

Data Index: 710356 (C4 (Web Text))

Max Activating Token Index: 259

Text #16

Max Range: 5.3441. Min Range: -5.3441

Max Act: 4.4988. Min Act: -0.0000

Data Index: 565653 (C4 (Web Text))

Max Activating Token Index: 164

Text #17

Max Range: 5.3441. Min Range: -5.3441

Max Act: 4.4836. Min Act: -0.0000

Data Index: 11888 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 5.3441. Min Range: -5.3441

Max Act: 4.5274. Min Act: -0.0000

Data Index: 565900 (C4 (Web Text))

Max Activating Token Index: 937

Text #19

Max Range: 5.3441. Min Range: -5.3441

Max Act: 4.2876. Min Act: -0.0000

Data Index: 446738 (C4 (Web Text))

Max Activating Token Index: 723