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

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

Neuron 4274 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1073. Min Range: -4.1073

Max Act: 4.1073. Min Act: -0.0000

Data Index: 1117386 (C4 (Web Text))

Max Activating Token Index: 231

Text #1

Max Range: 4.1073. Min Range: -4.1073

Max Act: 3.6514. Min Act: -0.0000

Data Index: 1050443 (C4 (Web Text))

Max Activating Token Index: 439

Text #2

Max Range: 4.1073. Min Range: -4.1073

Max Act: 3.4149. Min Act: -0.0000

Data Index: 989981 (C4 (Web Text))

Max Activating Token Index: 153

Text #3

Max Range: 4.1073. Min Range: -4.1073

Max Act: 3.3546. Min Act: -0.0000

Data Index: 1287405 (C4 (Web Text))

Max Activating Token Index: 812

Text #4

Max Range: 4.1073. Min Range: -4.1073

Max Act: 3.3003. Min Act: -0.0000

Data Index: 7458 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 4.1073. Min Range: -4.1073

Max Act: 3.2927. Min Act: -0.0000

Data Index: 593682 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 4.1073. Min Range: -4.1073

Max Act: 3.3561. Min Act: -0.0000

Data Index: 1059330 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 4.1073. Min Range: -4.1073

Max Act: 3.1086. Min Act: -0.0000

Data Index: 426705 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 4.1073. Min Range: -4.1073

Max Act: 2.9613. Min Act: -0.0000

Data Index: 106496 (C4 (Web Text))

Max Activating Token Index: 865

Text #9

Max Range: 4.1073. Min Range: -4.1073

Max Act: 3.0732. Min Act: -0.0000

Data Index: 1299666 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 4.1073. Min Range: -4.1073

Max Act: 3.2046. Min Act: -0.0000

Data Index: 566180 (C4 (Web Text))

Max Activating Token Index: 314

Text #11

Max Range: 4.1073. Min Range: -4.1073

Max Act: 3.0010. Min Act: -0.0000

Data Index: 372534 (C4 (Web Text))

Max Activating Token Index: 574

Text #12

Max Range: 4.1073. Min Range: -4.1073

Max Act: 2.9747. Min Act: -0.0000

Data Index: 1109235 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 4.1073. Min Range: -4.1073

Max Act: 2.9365. Min Act: -0.0000

Data Index: 742958 (C4 (Web Text))

Max Activating Token Index: 540

Text #14

Max Range: 4.1073. Min Range: -4.1073

Max Act: 2.8948. Min Act: -0.0000

Data Index: 1130346 (C4 (Web Text))

Max Activating Token Index: 598

Text #15

Max Range: 4.1073. Min Range: -4.1073

Max Act: 2.8518. Min Act: -0.0000

Data Index: 1295619 (C4 (Web Text))

Max Activating Token Index: 816

Text #16

Max Range: 4.1073. Min Range: -4.1073

Max Act: 2.8650. Min Act: -0.0000

Data Index: 936688 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 4.1073. Min Range: -4.1073

Max Act: 2.8121. Min Act: -0.0000

Data Index: 676291 (C4 (Web Text))

Max Activating Token Index: 447

Text #18

Max Range: 4.1073. Min Range: -4.1073

Max Act: 2.6689. Min Act: -0.0000

Data Index: 357036 (C4 (Web Text))

Max Activating Token Index: 621

Text #19

Max Range: 4.1073. Min Range: -4.1073

Max Act: 2.6679. Min Act: -0.0000

Data Index: 1354050 (C4 (Web Text))

Max Activating Token Index: 503