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

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

Neuron 4070 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: 0.4959. Min Range: -0.4959

Max Act: 0.4959. Min Act: -0.0000

Data Index: 331092 (C4 (Web Text))

Max Activating Token Index: 107

Text #1

Max Range: 0.4959. Min Range: -0.4959

Max Act: 0.4916. Min Act: -0.0000

Data Index: 418142 (C4 (Web Text))

Max Activating Token Index: 316

Text #2

Max Range: 0.4959. Min Range: -0.4959

Max Act: 0.4415. Min Act: -0.0000

Data Index: 1319436 (C4 (Web Text))

Max Activating Token Index: 570

Text #3

Max Range: 0.4959. Min Range: -0.4959

Max Act: 0.4220. Min Act: -0.0000

Data Index: 317706 (C4 (Web Text))

Max Activating Token Index: 959

Text #4

Max Range: 0.4959. Min Range: -0.4959

Max Act: 0.4105. Min Act: -0.0000

Data Index: 38538 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 0.4959. Min Range: -0.4959

Max Act: 0.4295. Min Act: -0.0000

Data Index: 410602 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 0.4959. Min Range: -0.4959

Max Act: 0.4361. Min Act: -0.0000

Data Index: 743311 (C4 (Web Text))

Max Activating Token Index: 926

Text #7

Max Range: 0.4959. Min Range: -0.4959

Max Act: 0.4117. Min Act: -0.0000

Data Index: 1108012 (C4 (Web Text))

Max Activating Token Index: 984

Text #8

Max Range: 0.4959. Min Range: -0.4959

Max Act: 0.4050. Min Act: -0.0000

Data Index: 1302364 (C4 (Web Text))

Max Activating Token Index: 528

Text #9

Max Range: 0.4959. Min Range: -0.4959

Max Act: 0.4311. Min Act: -0.0000

Data Index: 1186185 (C4 (Web Text))

Max Activating Token Index: 796

Text #10

Max Range: 0.4959. Min Range: -0.4959

Max Act: 0.3572. Min Act: -0.0000

Data Index: 132764 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 0.4959. Min Range: -0.4959

Max Act: 0.3527. Min Act: -0.0000

Data Index: 655756 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 0.4959. Min Range: -0.4959

Max Act: 0.4693. Min Act: -0.0000

Data Index: 1032086 (C4 (Web Text))

Max Activating Token Index: 861

Text #13

Max Range: 0.4959. Min Range: -0.4959

Max Act: 0.3904. Min Act: -0.0000

Data Index: 872151 (C4 (Web Text))

Max Activating Token Index: 935

Text #14

Max Range: 0.4959. Min Range: -0.4959

Max Act: 0.3596. Min Act: -0.0000

Data Index: 84707 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 0.4959. Min Range: -0.4959

Max Act: 0.3691. Min Act: -0.0000

Data Index: 909909 (C4 (Web Text))

Max Activating Token Index: 665

Text #16

Max Range: 0.4959. Min Range: -0.4959

Max Act: 0.3657. Min Act: -0.0000

Data Index: 648959 (C4 (Web Text))

Max Activating Token Index: 343

Text #17

Max Range: 0.4959. Min Range: -0.4959

Max Act: 0.3652. Min Act: -0.0000

Data Index: 1328176 (C4 (Web Text))

Max Activating Token Index: 470

Text #18

Max Range: 0.4959. Min Range: -0.4959

Max Act: 0.3538. Min Act: -0.0000

Data Index: 342827 (C4 (Web Text))

Max Activating Token Index: 853

Text #19

Max Range: 0.4959. Min Range: -0.4959

Max Act: 0.3752. Min Act: -0.0000

Data Index: 722077 (C4 (Web Text))

Max Activating Token Index: 256