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

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

Neuron 2510 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6327. Min Range: -2.6327

Max Act: 2.6327. Min Act: -0.0000

Data Index: 358966 (C4 (Web Text))

Max Activating Token Index: 382

Text #1

Max Range: 2.6327. Min Range: -2.6327

Max Act: 2.4016. Min Act: -0.0000

Data Index: 1456028 (Python Code)

Max Activating Token Index: 867

Text #2

Max Range: 2.6327. Min Range: -2.6327

Max Act: 2.3053. Min Act: -0.0000

Data Index: 847639 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 2.6327. Min Range: -2.6327

Max Act: 2.2941. Min Act: -0.0000

Data Index: 516894 (C4 (Web Text))

Max Activating Token Index: 497

Text #4

Max Range: 2.6327. Min Range: -2.6327

Max Act: 2.2730. Min Act: -0.0000

Data Index: 1581234 (Python Code)

Max Activating Token Index: 620

Text #5

Max Range: 2.6327. Min Range: -2.6327

Max Act: 2.2322. Min Act: -0.0000

Data Index: 792073 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 2.6327. Min Range: -2.6327

Max Act: 2.2145. Min Act: -0.0000

Data Index: 217591 (C4 (Web Text))

Max Activating Token Index: 157

Text #7

Max Range: 2.6327. Min Range: -2.6327

Max Act: 2.0876. Min Act: -0.0000

Data Index: 534437 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 2.6327. Min Range: -2.6327

Max Act: 2.1376. Min Act: -0.0000

Data Index: 1331493 (C4 (Web Text))

Max Activating Token Index: 800

Text #9

Max Range: 2.6327. Min Range: -2.6327

Max Act: 2.1331. Min Act: -0.0000

Data Index: 1244592 (C4 (Web Text))

Max Activating Token Index: 792

Text #10

Max Range: 2.6327. Min Range: -2.6327

Max Act: 2.1034. Min Act: -0.0000

Data Index: 1100004 (C4 (Web Text))

Max Activating Token Index: 193

Text #11

Max Range: 2.6327. Min Range: -2.6327

Max Act: 2.0914. Min Act: -0.0000

Data Index: 896672 (C4 (Web Text))

Max Activating Token Index: 128

Text #12

Max Range: 2.6327. Min Range: -2.6327

Max Act: 2.0964. Min Act: -0.0000

Data Index: 1266513 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 2.6327. Min Range: -2.6327

Max Act: 2.0763. Min Act: -0.0000

Data Index: 1249356 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 2.6327. Min Range: -2.6327

Max Act: 2.0890. Min Act: -0.0000

Data Index: 854364 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 2.6327. Min Range: -2.6327

Max Act: 2.0595. Min Act: -0.0000

Data Index: 1184322 (C4 (Web Text))

Max Activating Token Index: 573

Text #16

Max Range: 2.6327. Min Range: -2.6327

Max Act: 2.0367. Min Act: -0.0000

Data Index: 247550 (C4 (Web Text))

Max Activating Token Index: 875

Text #17

Max Range: 2.6327. Min Range: -2.6327

Max Act: 2.0366. Min Act: -0.0000

Data Index: 822700 (C4 (Web Text))

Max Activating Token Index: 174

Text #18

Max Range: 2.6327. Min Range: -2.6327

Max Act: 1.9872. Min Act: -0.0000

Data Index: 281088 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 2.6327. Min Range: -2.6327

Max Act: 1.9706. Min Act: -0.0000

Data Index: 1196060 (C4 (Web Text))

Max Activating Token Index: 9