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

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

Neuron 5923 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: 0.5005. Min Range: -0.5005

Max Act: 0.4890. Min Act: -0.0000

Data Index: 938832 (C4 (Web Text))

Max Activating Token Index: 210

Text #1

Max Range: 0.5005. Min Range: -0.5005

Max Act: 0.4513. Min Act: -0.0000

Data Index: 1449710 (Python Code)

Max Activating Token Index: 552

Text #2

Max Range: 0.5005. Min Range: -0.5005

Max Act: 0.5005. Min Act: -0.0000

Data Index: 662581 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 0.5005. Min Range: -0.5005

Max Act: 0.4854. Min Act: -0.0000

Data Index: 173297 (C4 (Web Text))

Max Activating Token Index: 269

Text #4

Max Range: 0.5005. Min Range: -0.5005

Max Act: 0.4743. Min Act: -0.0000

Data Index: 1380372 (Python Code)

Max Activating Token Index: 830

Text #5

Max Range: 0.5005. Min Range: -0.5005

Max Act: 0.4649. Min Act: -0.0000

Data Index: 1349483 (C4 (Web Text))

Max Activating Token Index: 592

Text #6

Max Range: 0.5005. Min Range: -0.5005

Max Act: 0.4082. Min Act: -0.0000

Data Index: 1490044 (Python Code)

Max Activating Token Index: 391

Text #7

Max Range: 0.5005. Min Range: -0.5005

Max Act: 0.4733. Min Act: -0.0000

Data Index: 1034323 (C4 (Web Text))

Max Activating Token Index: 370

Text #8

Max Range: 0.5005. Min Range: -0.5005

Max Act: 0.4395. Min Act: -0.0000

Data Index: 760466 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 0.5005. Min Range: -0.5005

Max Act: 0.4211. Min Act: -0.0000

Data Index: 1428413 (Python Code)

Max Activating Token Index: 660

Text #10

Max Range: 0.5005. Min Range: -0.5005

Max Act: 0.4007. Min Act: -0.0000

Data Index: 1440727 (Python Code)

Max Activating Token Index: 99

Text #11

Max Range: 0.5005. Min Range: -0.5005

Max Act: 0.4109. Min Act: -0.0000

Data Index: 1615672 (Python Code)

Max Activating Token Index: 608

Text #12

Max Range: 0.5005. Min Range: -0.5005

Max Act: 0.4087. Min Act: -0.0000

Data Index: 1420450 (Python Code)

Max Activating Token Index: 128

Text #13

Max Range: 0.5005. Min Range: -0.5005

Max Act: 0.4092. Min Act: -0.0000

Data Index: 12397 (C4 (Web Text))

Max Activating Token Index: 202

Text #14

Max Range: 0.5005. Min Range: -0.5005

Max Act: 0.4099. Min Act: -0.0000

Data Index: 289612 (C4 (Web Text))

Max Activating Token Index: 163

Text #15

Max Range: 0.5005. Min Range: -0.5005

Max Act: 0.4019. Min Act: -0.0000

Data Index: 170752 (C4 (Web Text))

Max Activating Token Index: 636

Text #16

Max Range: 0.5005. Min Range: -0.5005

Max Act: 0.4186. Min Act: -0.0000

Data Index: 1598472 (Python Code)

Max Activating Token Index: 971

Text #17

Max Range: 0.5005. Min Range: -0.5005

Max Act: 0.3663. Min Act: -0.0000

Data Index: 1164199 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 0.5005. Min Range: -0.5005

Max Act: 0.4014. Min Act: -0.0000

Data Index: 958294 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 0.5005. Min Range: -0.5005

Max Act: 0.3576. Min Act: -0.0000

Data Index: 1461315 (Python Code)

Max Activating Token Index: 52