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

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

Neuron 3090 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1435. Min Act: -0.0002

Data Index: 1237674 (C4 (Web Text))

Max Activating Token Index: 420

Text #1

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1388. Min Act: -0.0002

Data Index: 461417 (C4 (Web Text))

Max Activating Token Index: 46

Text #2

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1279. Min Act: -0.0002

Data Index: 91337 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1247. Min Act: -0.0002

Data Index: 143973 (C4 (Web Text))

Max Activating Token Index: 645

Text #4

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1246. Min Act: -0.0002

Data Index: 999593 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1187. Min Act: -0.0002

Data Index: 713080 (C4 (Web Text))

Max Activating Token Index: 935

Text #6

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1141. Min Act: -0.0002

Data Index: 587344 (C4 (Web Text))

Max Activating Token Index: 472

Text #7

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1143. Min Act: -0.0002

Data Index: 1028506 (C4 (Web Text))

Max Activating Token Index: 817

Text #8

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1119. Min Act: -0.0002

Data Index: 194673 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1080. Min Act: -0.0002

Data Index: 126374 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1030. Min Act: -0.0002

Data Index: 171884 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1070. Min Act: -0.0002

Data Index: 434326 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1048. Min Act: -0.0002

Data Index: 588968 (C4 (Web Text))

Max Activating Token Index: 63

Text #13

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1026. Min Act: -0.0002

Data Index: 648759 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1023. Min Act: -0.0002

Data Index: 818586 (C4 (Web Text))

Max Activating Token Index: 516

Text #15

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1019. Min Act: -0.0002

Data Index: 244717 (C4 (Web Text))

Max Activating Token Index: 579

Text #16

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1009. Min Act: -0.0002

Data Index: 54479 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1002. Min Act: -0.0002

Data Index: 310395 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.0992. Min Act: -0.0002

Data Index: 413502 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.0992. Min Act: -0.0002

Data Index: 330950 (C4 (Web Text))

Max Activating Token Index: 146