Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1663 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.4391. Min Act: -0.0000

Data Index: 995665 (C4 (Web Text))

Max Activating Token Index: 106

Text #1

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3979. Min Act: -0.0000

Data Index: 130235 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.4106. Min Act: -0.0000

Data Index: 506809 (C4 (Web Text))

Max Activating Token Index: 830

Text #3

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.4112. Min Act: -0.0000

Data Index: 258714 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.4030. Min Act: -0.0000

Data Index: 47254 (C4 (Web Text))

Max Activating Token Index: 603

Text #5

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.4422. Min Act: -0.0000

Data Index: 197812 (C4 (Web Text))

Max Activating Token Index: 670

Text #6

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3791. Min Act: -0.0000

Data Index: 1138794 (C4 (Web Text))

Max Activating Token Index: 147

Text #7

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.4056. Min Act: -0.0000

Data Index: 180838 (C4 (Web Text))

Max Activating Token Index: 725

Text #8

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3685. Min Act: -0.0000

Data Index: 1192784 (C4 (Web Text))

Max Activating Token Index: 626

Text #9

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.4083. Min Act: -0.0000

Data Index: 543436 (C4 (Web Text))

Max Activating Token Index: 1011

Text #10

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.4042. Min Act: -0.0000

Data Index: 971727 (C4 (Web Text))

Max Activating Token Index: 900

Text #11

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3826. Min Act: -0.0000

Data Index: 1212365 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3789. Min Act: -0.0000

Data Index: 658946 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3280. Min Act: -0.0000

Data Index: 1140312 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3477. Min Act: -0.0000

Data Index: 1164788 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3523. Min Act: -0.0000

Data Index: 660591 (C4 (Web Text))

Max Activating Token Index: 861

Text #16

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3279. Min Act: -0.0000

Data Index: 434844 (C4 (Web Text))

Max Activating Token Index: 665

Text #17

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3321. Min Act: -0.0000

Data Index: 1153199 (C4 (Web Text))

Max Activating Token Index: 360

Text #18

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3203. Min Act: -0.0000

Data Index: 18473 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3416. Min Act: -0.0000

Data Index: 289796 (C4 (Web Text))

Max Activating Token Index: 959