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

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

Neuron 6028 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: 2.9352. Min Range: -2.9352

Max Act: 2.9352. Min Act: -0.0000

Data Index: 1101420 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 2.9352. Min Range: -2.9352

Max Act: 2.6595. Min Act: -0.0000

Data Index: 1189249 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 2.9352. Min Range: -2.9352

Max Act: 2.6595. Min Act: -0.0000

Data Index: 1225867 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 2.9352. Min Range: -2.9352

Max Act: 2.6962. Min Act: -0.0000

Data Index: 204677 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 2.9352. Min Range: -2.9352

Max Act: 2.6092. Min Act: -0.0000

Data Index: 431103 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 2.9352. Min Range: -2.9352

Max Act: 2.6065. Min Act: -0.0000

Data Index: 669166 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 2.9352. Min Range: -2.9352

Max Act: 2.4099. Min Act: -0.0000

Data Index: 339692 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 2.9352. Min Range: -2.9352

Max Act: 2.5101. Min Act: -0.0000

Data Index: 282293 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 2.9352. Min Range: -2.9352

Max Act: 2.4629. Min Act: -0.0000

Data Index: 252248 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 2.9352. Min Range: -2.9352

Max Act: 2.4653. Min Act: -0.0000

Data Index: 190574 (C4 (Web Text))

Max Activating Token Index: 597

Text #10

Max Range: 2.9352. Min Range: -2.9352

Max Act: 2.4293. Min Act: -0.0000

Data Index: 907203 (C4 (Web Text))

Max Activating Token Index: 737

Text #11

Max Range: 2.9352. Min Range: -2.9352

Max Act: 2.5453. Min Act: -0.0000

Data Index: 667284 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 2.9352. Min Range: -2.9352

Max Act: 2.4186. Min Act: -0.0000

Data Index: 399284 (C4 (Web Text))

Max Activating Token Index: 1008

Text #13

Max Range: 2.9352. Min Range: -2.9352

Max Act: 2.2791. Min Act: -0.0000

Data Index: 1145146 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 2.9352. Min Range: -2.9352

Max Act: 2.3938. Min Act: -0.0000

Data Index: 267383 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 2.9352. Min Range: -2.9352

Max Act: 2.3823. Min Act: -0.0000

Data Index: 905352 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 2.9352. Min Range: -2.9352

Max Act: 2.3784. Min Act: -0.0000

Data Index: 18119 (C4 (Web Text))

Max Activating Token Index: 155

Text #17

Max Range: 2.9352. Min Range: -2.9352

Max Act: 2.3734. Min Act: -0.0000

Data Index: 177020 (C4 (Web Text))

Max Activating Token Index: 892

Text #18

Max Range: 2.9352. Min Range: -2.9352

Max Act: 2.3490. Min Act: -0.0000

Data Index: 235098 (C4 (Web Text))

Max Activating Token Index: 805

Text #19

Max Range: 2.9352. Min Range: -2.9352

Max Act: 2.1979. Min Act: -0.0000

Data Index: 438716 (C4 (Web Text))

Max Activating Token Index: 524