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

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

Neuron 1821 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: 1.3132. Min Range: -1.3132

Max Act: 1.3132. Min Act: -0.0000

Data Index: 108828 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 1.3132. Min Range: -1.3132

Max Act: 1.1418. Min Act: -0.0000

Data Index: 652600 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 1.3132. Min Range: -1.3132

Max Act: 1.1431. Min Act: -0.0000

Data Index: 180622 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 1.3132. Min Range: -1.3132

Max Act: 1.2236. Min Act: -0.0000

Data Index: 675504 (C4 (Web Text))

Max Activating Token Index: 716

Text #4

Max Range: 1.3132. Min Range: -1.3132

Max Act: 1.0792. Min Act: -0.0000

Data Index: 400918 (C4 (Web Text))

Max Activating Token Index: 485

Text #5

Max Range: 1.3132. Min Range: -1.3132

Max Act: 1.0320. Min Act: -0.0000

Data Index: 327234 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 1.3132. Min Range: -1.3132

Max Act: 1.0700. Min Act: -0.0000

Data Index: 397471 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 1.3132. Min Range: -1.3132

Max Act: 1.0546. Min Act: -0.0000

Data Index: 909260 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 1.3132. Min Range: -1.3132

Max Act: 1.0501. Min Act: -0.0000

Data Index: 655622 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 1.3132. Min Range: -1.3132

Max Act: 1.0404. Min Act: -0.0000

Data Index: 7802 (C4 (Web Text))

Max Activating Token Index: 150

Text #10

Max Range: 1.3132. Min Range: -1.3132

Max Act: 1.0017. Min Act: -0.0000

Data Index: 952654 (C4 (Web Text))

Max Activating Token Index: 246

Text #11

Max Range: 1.3132. Min Range: -1.3132

Max Act: 1.0092. Min Act: -0.0000

Data Index: 1058185 (C4 (Web Text))

Max Activating Token Index: 768

Text #12

Max Range: 1.3132. Min Range: -1.3132

Max Act: 0.9991. Min Act: -0.0000

Data Index: 623476 (C4 (Web Text))

Max Activating Token Index: 138

Text #13

Max Range: 1.3132. Min Range: -1.3132

Max Act: 0.9343. Min Act: -0.0000

Data Index: 410916 (C4 (Web Text))

Max Activating Token Index: 653

Text #14

Max Range: 1.3132. Min Range: -1.3132

Max Act: 0.9850. Min Act: -0.0000

Data Index: 1035002 (C4 (Web Text))

Max Activating Token Index: 600

Text #15

Max Range: 1.3132. Min Range: -1.3132

Max Act: 0.8535. Min Act: -0.0000

Data Index: 1280811 (C4 (Web Text))

Max Activating Token Index: 811

Text #16

Max Range: 1.3132. Min Range: -1.3132

Max Act: 0.8585. Min Act: -0.0000

Data Index: 1160256 (C4 (Web Text))

Max Activating Token Index: 903

Text #17

Max Range: 1.3132. Min Range: -1.3132

Max Act: 0.9615. Min Act: -0.0000

Data Index: 78136 (C4 (Web Text))

Max Activating Token Index: 277

Text #18

Max Range: 1.3132. Min Range: -1.3132

Max Act: 0.9669. Min Act: -0.0000

Data Index: 852615 (C4 (Web Text))

Max Activating Token Index: 391

Text #19

Max Range: 1.3132. Min Range: -1.3132

Max Act: 0.9024. Min Act: -0.0000

Data Index: 1281155 (C4 (Web Text))

Max Activating Token Index: 885