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

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

Neuron 633 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: 0.8723. Min Range: -0.8723

Max Act: 0.8723. Min Act: -0.0000

Data Index: 699593 (C4 (Web Text))

Max Activating Token Index: 274

Text #1

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.7809. Min Act: -0.0000

Data Index: 106590 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.7678. Min Act: -0.0000

Data Index: 1088914 (C4 (Web Text))

Max Activating Token Index: 670

Text #3

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.7011. Min Act: -0.0000

Data Index: 141966 (C4 (Web Text))

Max Activating Token Index: 155

Text #4

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.7156. Min Act: -0.0000

Data Index: 127934 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.6280. Min Act: -0.0000

Data Index: 83429 (C4 (Web Text))

Max Activating Token Index: 930

Text #6

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.6748. Min Act: -0.0000

Data Index: 627897 (C4 (Web Text))

Max Activating Token Index: 794

Text #7

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.5774. Min Act: -0.0000

Data Index: 925767 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.5720. Min Act: -0.0000

Data Index: 916753 (C4 (Web Text))

Max Activating Token Index: 748

Text #9

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.5824. Min Act: 0.0000

Data Index: 1195901 (C4 (Web Text))

Max Activating Token Index: 259

Text #10

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.4991. Min Act: -0.0000

Data Index: 662749 (C4 (Web Text))

Max Activating Token Index: 449

Text #11

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.5654. Min Act: -0.0000

Data Index: 527934 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.5306. Min Act: -0.0000

Data Index: 543649 (C4 (Web Text))

Max Activating Token Index: 183

Text #13

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.5174. Min Act: -0.0000

Data Index: 304413 (C4 (Web Text))

Max Activating Token Index: 520

Text #14

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.5304. Min Act: -0.0000

Data Index: 633408 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.4943. Min Act: -0.0000

Data Index: 138605 (C4 (Web Text))

Max Activating Token Index: 127

Text #16

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.5129. Min Act: -0.0000

Data Index: 1270480 (C4 (Web Text))

Max Activating Token Index: 598

Text #17

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.5000. Min Act: -0.0000

Data Index: 931056 (C4 (Web Text))

Max Activating Token Index: 838

Text #18

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.4848. Min Act: -0.0000

Data Index: 426219 (C4 (Web Text))

Max Activating Token Index: 374

Text #19

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.4817. Min Act: 0.0000

Data Index: 467722 (C4 (Web Text))

Max Activating Token Index: 594