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

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

Neuron 854 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.9605. Min Act: -0.0000

Data Index: 1112756 (C4 (Web Text))

Max Activating Token Index: 726

Text #1

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.8300. Min Act: -0.0001

Data Index: 264314 (C4 (Web Text))

Max Activating Token Index: 403

Text #2

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.8082. Min Act: -0.0001

Data Index: 840496 (C4 (Web Text))

Max Activating Token Index: 207

Text #3

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.7951. Min Act: -0.0001

Data Index: 340063 (C4 (Web Text))

Max Activating Token Index: 210

Text #4

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.7581. Min Act: -0.0000

Data Index: 383780 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.7914. Min Act: -0.0001

Data Index: 329389 (C4 (Web Text))

Max Activating Token Index: 672

Text #6

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.7034. Min Act: -0.0001

Data Index: 1335005 (C4 (Web Text))

Max Activating Token Index: 187

Text #7

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.6785. Min Act: -0.0001

Data Index: 950115 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.7191. Min Act: -0.0001

Data Index: 21997 (C4 (Web Text))

Max Activating Token Index: 983

Text #9

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.6737. Min Act: -0.0001

Data Index: 556747 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.6522. Min Act: -0.0001

Data Index: 249820 (C4 (Web Text))

Max Activating Token Index: 482

Text #11

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.6807. Min Act: -0.0000

Data Index: 547276 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.6577. Min Act: -0.0001

Data Index: 1323688 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.6590. Min Act: -0.0000

Data Index: 643777 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.6150. Min Act: -0.0001

Data Index: 612655 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.6477. Min Act: -0.0001

Data Index: 390682 (C4 (Web Text))

Max Activating Token Index: 7

Text #16

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.6603. Min Act: -0.0001

Data Index: 775656 (C4 (Web Text))

Max Activating Token Index: 351

Text #17

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.6233. Min Act: -0.0001

Data Index: 166233 (C4 (Web Text))

Max Activating Token Index: 556

Text #18

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.6184. Min Act: -0.0001

Data Index: 1308178 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.5585. Min Act: -0.0001

Data Index: 1343358 (C4 (Web Text))

Max Activating Token Index: 710