Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2171 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.4172. Min Act: -0.0000

Data Index: 322214 (C4 (Web Text))

Max Activating Token Index: 798

Text #1

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.3764. Min Act: -0.0000

Data Index: 19451 (C4 (Web Text))

Max Activating Token Index: 872

Text #2

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.3446. Min Act: -0.0000

Data Index: 1117527 (C4 (Web Text))

Max Activating Token Index: 609

Text #3

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.3377. Min Act: -0.0000

Data Index: 1055342 (C4 (Web Text))

Max Activating Token Index: 719

Text #4

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.3523. Min Act: -0.0000

Data Index: 829722 (C4 (Web Text))

Max Activating Token Index: 434

Text #5

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.3318. Min Act: -0.0000

Data Index: 67302 (C4 (Web Text))

Max Activating Token Index: 634

Text #6

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.3257. Min Act: -0.0000

Data Index: 886211 (C4 (Web Text))

Max Activating Token Index: 289

Text #7

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.3052. Min Act: -0.0000

Data Index: 1051172 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.3294. Min Act: -0.0000

Data Index: 180683 (C4 (Web Text))

Max Activating Token Index: 901

Text #9

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.3146. Min Act: -0.0000

Data Index: 866960 (C4 (Web Text))

Max Activating Token Index: 273

Text #10

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.3030. Min Act: -0.0000

Data Index: 590738 (C4 (Web Text))

Max Activating Token Index: 539

Text #11

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.2955. Min Act: -0.0000

Data Index: 627775 (C4 (Web Text))

Max Activating Token Index: 790

Text #12

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.3008. Min Act: -0.0000

Data Index: 1070402 (C4 (Web Text))

Max Activating Token Index: 804

Text #13

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.3023. Min Act: -0.0000

Data Index: 1059697 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.3018. Min Act: -0.0000

Data Index: 708476 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.3083. Min Act: -0.0000

Data Index: 1269590 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.3097. Min Act: -0.0000

Data Index: 794618 (C4 (Web Text))

Max Activating Token Index: 469

Text #17

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.2955. Min Act: -0.0000

Data Index: 432464 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.2912. Min Act: -0.0000

Data Index: 219609 (C4 (Web Text))

Max Activating Token Index: 1013

Text #19

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.3033. Min Act: -0.0000

Data Index: 931459 (C4 (Web Text))

Max Activating Token Index: 259