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

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

Neuron 1599 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: 3.7138. Min Range: -3.7138

Max Act: 3.7138. Min Act: -0.0000

Data Index: 283407 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 3.7138. Min Range: -3.7138

Max Act: 3.6274. Min Act: -0.0000

Data Index: 988438 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 3.7138. Min Range: -3.7138

Max Act: 3.2416. Min Act: -0.0000

Data Index: 199555 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 3.7138. Min Range: -3.7138

Max Act: 3.3642. Min Act: -0.0000

Data Index: 725122 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 3.7138. Min Range: -3.7138

Max Act: 3.3691. Min Act: -0.0000

Data Index: 1171297 (C4 (Web Text))

Max Activating Token Index: 801

Text #5

Max Range: 3.7138. Min Range: -3.7138

Max Act: 3.2563. Min Act: -0.0000

Data Index: 377554 (C4 (Web Text))

Max Activating Token Index: 571

Text #6

Max Range: 3.7138. Min Range: -3.7138

Max Act: 3.0766. Min Act: -0.0000

Data Index: 21303 (C4 (Web Text))

Max Activating Token Index: 482

Text #7

Max Range: 3.7138. Min Range: -3.7138

Max Act: 2.9426. Min Act: -0.0000

Data Index: 1131823 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 3.7138. Min Range: -3.7138

Max Act: 2.9267. Min Act: -0.0000

Data Index: 1096143 (C4 (Web Text))

Max Activating Token Index: 925

Text #9

Max Range: 3.7138. Min Range: -3.7138

Max Act: 2.9186. Min Act: -0.0000

Data Index: 591980 (C4 (Web Text))

Max Activating Token Index: 329

Text #10

Max Range: 3.7138. Min Range: -3.7138

Max Act: 3.1632. Min Act: -0.0000

Data Index: 74784 (C4 (Web Text))

Max Activating Token Index: 173

Text #11

Max Range: 3.7138. Min Range: -3.7138

Max Act: 3.1253. Min Act: -0.0000

Data Index: 476276 (C4 (Web Text))

Max Activating Token Index: 736

Text #12

Max Range: 3.7138. Min Range: -3.7138

Max Act: 2.9880. Min Act: -0.0000

Data Index: 1076656 (C4 (Web Text))

Max Activating Token Index: 62

Text #13

Max Range: 3.7138. Min Range: -3.7138

Max Act: 3.1263. Min Act: -0.0000

Data Index: 844540 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 3.7138. Min Range: -3.7138

Max Act: 3.2774. Min Act: -0.0000

Data Index: 1094779 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 3.7138. Min Range: -3.7138

Max Act: 2.1898. Min Act: -0.0000

Data Index: 851396 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 3.7138. Min Range: -3.7138

Max Act: 2.9044. Min Act: -0.0000

Data Index: 748089 (C4 (Web Text))

Max Activating Token Index: 645

Text #17

Max Range: 3.7138. Min Range: -3.7138

Max Act: 3.1693. Min Act: -0.0000

Data Index: 502131 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 3.7138. Min Range: -3.7138

Max Act: 2.9139. Min Act: -0.0000

Data Index: 1008818 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 3.7138. Min Range: -3.7138

Max Act: 2.8940. Min Act: -0.0000

Data Index: 729331 (C4 (Web Text))

Max Activating Token Index: 803