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

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

Neuron 2819 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7377. Min Range: -3.7377

Max Act: 3.7377. Min Act: -0.0000

Data Index: 1166415 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 3.7377. Min Range: -3.7377

Max Act: 3.5097. Min Act: -0.0000

Data Index: 320358 (C4 (Web Text))

Max Activating Token Index: 897

Text #2

Max Range: 3.7377. Min Range: -3.7377

Max Act: 3.3344. Min Act: -0.0000

Data Index: 324508 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 3.7377. Min Range: -3.7377

Max Act: 3.1787. Min Act: -0.0000

Data Index: 568624 (C4 (Web Text))

Max Activating Token Index: 991

Text #4

Max Range: 3.7377. Min Range: -3.7377

Max Act: 3.2456. Min Act: -0.0000

Data Index: 621816 (C4 (Web Text))

Max Activating Token Index: 538

Text #5

Max Range: 3.7377. Min Range: -3.7377

Max Act: 3.1987. Min Act: -0.0000

Data Index: 840394 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 3.7377. Min Range: -3.7377

Max Act: 3.1270. Min Act: -0.0000

Data Index: 1159048 (C4 (Web Text))

Max Activating Token Index: 605

Text #7

Max Range: 3.7377. Min Range: -3.7377

Max Act: 2.9016. Min Act: -0.0000

Data Index: 1188959 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 3.7377. Min Range: -3.7377

Max Act: 3.0009. Min Act: -0.0000

Data Index: 985872 (C4 (Web Text))

Max Activating Token Index: 235

Text #9

Max Range: 3.7377. Min Range: -3.7377

Max Act: 2.9531. Min Act: -0.0000

Data Index: 333182 (C4 (Web Text))

Max Activating Token Index: 848

Text #10

Max Range: 3.7377. Min Range: -3.7377

Max Act: 2.8129. Min Act: -0.0000

Data Index: 1326773 (C4 (Web Text))

Max Activating Token Index: 588

Text #11

Max Range: 3.7377. Min Range: -3.7377

Max Act: 3.0850. Min Act: -0.0000

Data Index: 1521526 (Python Code)

Max Activating Token Index: 9

Text #12

Max Range: 3.7377. Min Range: -3.7377

Max Act: 2.7973. Min Act: -0.0000

Data Index: 161545 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 3.7377. Min Range: -3.7377

Max Act: 3.0157. Min Act: -0.0000

Data Index: 1574050 (Python Code)

Max Activating Token Index: 563

Text #14

Max Range: 3.7377. Min Range: -3.7377

Max Act: 2.8597. Min Act: -0.0000

Data Index: 389848 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 3.7377. Min Range: -3.7377

Max Act: 2.9810. Min Act: -0.0000

Data Index: 400058 (C4 (Web Text))

Max Activating Token Index: 739

Text #16

Max Range: 3.7377. Min Range: -3.7377

Max Act: 2.8716. Min Act: -0.0000

Data Index: 839343 (C4 (Web Text))

Max Activating Token Index: 979

Text #17

Max Range: 3.7377. Min Range: -3.7377

Max Act: 2.7385. Min Act: -0.0000

Data Index: 755580 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 3.7377. Min Range: -3.7377

Max Act: 2.6208. Min Act: -0.0000

Data Index: 1097741 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 3.7377. Min Range: -3.7377

Max Act: 2.8404. Min Act: -0.0000

Data Index: 667342 (C4 (Web Text))

Max Activating Token Index: 602