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

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

Neuron 4438 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: 0.7554. Min Range: -0.7554

Max Act: 0.7554. Min Act: -0.0000

Data Index: 235438 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.6976. Min Act: -0.0000

Data Index: 1083537 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5978. Min Act: -0.0000

Data Index: 842430 (C4 (Web Text))

Max Activating Token Index: 114

Text #3

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.6252. Min Act: -0.0000

Data Index: 338336 (C4 (Web Text))

Max Activating Token Index: 859

Text #4

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5953. Min Act: -0.0000

Data Index: 764356 (C4 (Web Text))

Max Activating Token Index: 251

Text #5

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5289. Min Act: -0.0000

Data Index: 429327 (C4 (Web Text))

Max Activating Token Index: 960

Text #6

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5888. Min Act: -0.0000

Data Index: 1152934 (C4 (Web Text))

Max Activating Token Index: 225

Text #7

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5771. Min Act: -0.0000

Data Index: 368541 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5291. Min Act: -0.0000

Data Index: 1093396 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.6046. Min Act: -0.0000

Data Index: 1586737 (Python Code)

Max Activating Token Index: 730

Text #10

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5470. Min Act: -0.0000

Data Index: 1148918 (C4 (Web Text))

Max Activating Token Index: 763

Text #11

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5894. Min Act: -0.0000

Data Index: 775731 (C4 (Web Text))

Max Activating Token Index: 241

Text #12

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5866. Min Act: -0.0000

Data Index: 1104041 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5722. Min Act: -0.0000

Data Index: 95437 (C4 (Web Text))

Max Activating Token Index: 664

Text #14

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5452. Min Act: -0.0000

Data Index: 538503 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5361. Min Act: -0.0000

Data Index: 199244 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5469. Min Act: -0.0000

Data Index: 27144 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5296. Min Act: -0.0000

Data Index: 950464 (C4 (Web Text))

Max Activating Token Index: 341

Text #18

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5071. Min Act: -0.0000

Data Index: 1315710 (C4 (Web Text))

Max Activating Token Index: 895

Text #19

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5248. Min Act: -0.0000

Data Index: 710770 (C4 (Web Text))

Max Activating Token Index: 696