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

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

Neuron 3600 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: 0.6647. Min Range: -0.6647

Max Act: 0.6647. Min Act: -0.0000

Data Index: 1246647 (C4 (Web Text))

Max Activating Token Index: 194

Text #1

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.4724. Min Act: -0.0000

Data Index: 382170 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.4116. Min Act: -0.0000

Data Index: 1220944 (C4 (Web Text))

Max Activating Token Index: 405

Text #3

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.3998. Min Act: -0.0000

Data Index: 1306505 (C4 (Web Text))

Max Activating Token Index: 339

Text #4

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.3970. Min Act: -0.0000

Data Index: 421815 (C4 (Web Text))

Max Activating Token Index: 261

Text #5

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.4474. Min Act: -0.0000

Data Index: 1026136 (C4 (Web Text))

Max Activating Token Index: 372

Text #6

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.3088. Min Act: -0.0000

Data Index: 871673 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.3737. Min Act: -0.0000

Data Index: 1203788 (C4 (Web Text))

Max Activating Token Index: 654

Text #8

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.3493. Min Act: -0.0000

Data Index: 1230098 (C4 (Web Text))

Max Activating Token Index: 322

Text #9

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.3907. Min Act: -0.0000

Data Index: 1067625 (C4 (Web Text))

Max Activating Token Index: 724

Text #10

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.3501. Min Act: -0.0000

Data Index: 503739 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.3657. Min Act: -0.0000

Data Index: 110053 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.3518. Min Act: -0.0000

Data Index: 1408540 (Python Code)

Max Activating Token Index: 279

Text #13

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.3240. Min Act: 0.0000

Data Index: 1073671 (C4 (Web Text))

Max Activating Token Index: 407

Text #14

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.3149. Min Act: 0.0000

Data Index: 853458 (C4 (Web Text))

Max Activating Token Index: 139

Text #15

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.2744. Min Act: -0.0000

Data Index: 1136194 (C4 (Web Text))

Max Activating Token Index: 296

Text #16

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.3008. Min Act: -0.0000

Data Index: 128094 (C4 (Web Text))

Max Activating Token Index: 30

Text #17

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.3022. Min Act: 0.0000

Data Index: 676338 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.2984. Min Act: -0.0000

Data Index: 641612 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.3175. Min Act: -0.0000

Data Index: 1018370 (C4 (Web Text))

Max Activating Token Index: 910