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

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

Neuron 6077 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9177. Min Range: -2.9177

Max Act: 2.7683. Min Act: -0.0000

Data Index: 231815 (C4 (Web Text))

Max Activating Token Index: 263

Text #1

Max Range: 2.9177. Min Range: -2.9177

Max Act: 2.8334. Min Act: -0.0000

Data Index: 920641 (C4 (Web Text))

Max Activating Token Index: 268

Text #2

Max Range: 2.9177. Min Range: -2.9177

Max Act: 2.9177. Min Act: -0.0000

Data Index: 1132511 (C4 (Web Text))

Max Activating Token Index: 509

Text #3

Max Range: 2.9177. Min Range: -2.9177

Max Act: 2.5306. Min Act: -0.0000

Data Index: 168553 (C4 (Web Text))

Max Activating Token Index: 447

Text #4

Max Range: 2.9177. Min Range: -2.9177

Max Act: 2.9119. Min Act: -0.0000

Data Index: 256119 (C4 (Web Text))

Max Activating Token Index: 64

Text #5

Max Range: 2.9177. Min Range: -2.9177

Max Act: 2.6090. Min Act: -0.0000

Data Index: 798114 (C4 (Web Text))

Max Activating Token Index: 353

Text #6

Max Range: 2.9177. Min Range: -2.9177

Max Act: 2.6127. Min Act: -0.0000

Data Index: 499478 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 2.9177. Min Range: -2.9177

Max Act: 2.4989. Min Act: -0.0000

Data Index: 576914 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 2.9177. Min Range: -2.9177

Max Act: 2.6026. Min Act: -0.0000

Data Index: 20158 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 2.9177. Min Range: -2.9177

Max Act: 2.6550. Min Act: -0.0000

Data Index: 827327 (C4 (Web Text))

Max Activating Token Index: 574

Text #10

Max Range: 2.9177. Min Range: -2.9177

Max Act: 2.7880. Min Act: -0.0000

Data Index: 213939 (C4 (Web Text))

Max Activating Token Index: 644

Text #11

Max Range: 2.9177. Min Range: -2.9177

Max Act: 2.6277. Min Act: -0.0000

Data Index: 702972 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 2.9177. Min Range: -2.9177

Max Act: 2.5776. Min Act: -0.0000

Data Index: 445168 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 2.9177. Min Range: -2.9177

Max Act: 2.4956. Min Act: -0.0000

Data Index: 1331208 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 2.9177. Min Range: -2.9177

Max Act: 2.5790. Min Act: -0.0000

Data Index: 691575 (C4 (Web Text))

Max Activating Token Index: 449

Text #15

Max Range: 2.9177. Min Range: -2.9177

Max Act: 2.5610. Min Act: -0.0000

Data Index: 579814 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 2.9177. Min Range: -2.9177

Max Act: 2.1366. Min Act: -0.0000

Data Index: 361624 (C4 (Web Text))

Max Activating Token Index: 238

Text #17

Max Range: 2.9177. Min Range: -2.9177

Max Act: 2.4941. Min Act: -0.0000

Data Index: 1259121 (C4 (Web Text))

Max Activating Token Index: 579

Text #18

Max Range: 2.9177. Min Range: -2.9177

Max Act: 2.3563. Min Act: -0.0000

Data Index: 335825 (C4 (Web Text))

Max Activating Token Index: 400

Text #19

Max Range: 2.9177. Min Range: -2.9177

Max Act: 2.4347. Min Act: -0.0000

Data Index: 91231 (C4 (Web Text))

Max Activating Token Index: 736