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

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

Neuron 2712 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7849. Min Range: -3.7849

Max Act: 3.7849. Min Act: -0.0000

Data Index: 1054867 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 3.7849. Min Range: -3.7849

Max Act: 3.6557. Min Act: -0.0000

Data Index: 1006116 (C4 (Web Text))

Max Activating Token Index: 516

Text #2

Max Range: 3.7849. Min Range: -3.7849

Max Act: 3.1187. Min Act: -0.0000

Data Index: 672742 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 3.7849. Min Range: -3.7849

Max Act: 3.0280. Min Act: -0.0000

Data Index: 152791 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 3.7849. Min Range: -3.7849

Max Act: 2.9815. Min Act: -0.0000

Data Index: 166920 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 3.7849. Min Range: -3.7849

Max Act: 2.9619. Min Act: -0.0000

Data Index: 1151611 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 3.7849. Min Range: -3.7849

Max Act: 3.1049. Min Act: -0.0000

Data Index: 781809 (C4 (Web Text))

Max Activating Token Index: 594

Text #7

Max Range: 3.7849. Min Range: -3.7849

Max Act: 3.0789. Min Act: -0.0000

Data Index: 1161587 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 3.7849. Min Range: -3.7849

Max Act: 2.9740. Min Act: -0.0000

Data Index: 113874 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 3.7849. Min Range: -3.7849

Max Act: 2.8862. Min Act: -0.0000

Data Index: 6296 (C4 (Web Text))

Max Activating Token Index: 698

Text #10

Max Range: 3.7849. Min Range: -3.7849

Max Act: 2.8473. Min Act: -0.0000

Data Index: 1091276 (C4 (Web Text))

Max Activating Token Index: 64

Text #11

Max Range: 3.7849. Min Range: -3.7849

Max Act: 2.4623. Min Act: -0.0000

Data Index: 782410 (C4 (Web Text))

Max Activating Token Index: 275

Text #12

Max Range: 3.7849. Min Range: -3.7849

Max Act: 2.7453. Min Act: -0.0000

Data Index: 1231588 (C4 (Web Text))

Max Activating Token Index: 373

Text #13

Max Range: 3.7849. Min Range: -3.7849

Max Act: 2.6100. Min Act: -0.0000

Data Index: 497050 (C4 (Web Text))

Max Activating Token Index: 664

Text #14

Max Range: 3.7849. Min Range: -3.7849

Max Act: 2.5660. Min Act: -0.0000

Data Index: 461824 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 3.7849. Min Range: -3.7849

Max Act: 2.6613. Min Act: -0.0000

Data Index: 672946 (C4 (Web Text))

Max Activating Token Index: 344

Text #16

Max Range: 3.7849. Min Range: -3.7849

Max Act: 2.4510. Min Act: -0.0000

Data Index: 129683 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 3.7849. Min Range: -3.7849

Max Act: 2.4460. Min Act: -0.0000

Data Index: 588834 (C4 (Web Text))

Max Activating Token Index: 681

Text #18

Max Range: 3.7849. Min Range: -3.7849

Max Act: 2.6895. Min Act: -0.0000

Data Index: 447599 (C4 (Web Text))

Max Activating Token Index: 723

Text #19

Max Range: 3.7849. Min Range: -3.7849

Max Act: 2.4182. Min Act: -0.0000

Data Index: 52047 (C4 (Web Text))

Max Activating Token Index: 920