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

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

Neuron 5225 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0022. Min Range: -1.0022

Max Act: 1.0022. Min Act: -0.0000

Data Index: 334741 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.6112. Min Act: -0.0000

Data Index: 571314 (C4 (Web Text))

Max Activating Token Index: 927

Text #2

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.2074. Min Act: -0.0000

Data Index: 757205 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.0958. Min Act: -0.0000

Data Index: 378567 (C4 (Web Text))

Max Activating Token Index: 853

Text #4

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.0555. Min Act: -0.0000

Data Index: 430404 (C4 (Web Text))

Max Activating Token Index: 557

Text #5

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.0418. Min Act: -0.0000

Data Index: 1094936 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.0355. Min Act: -0.0000

Data Index: 1296612 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.0295. Min Act: -0.0000

Data Index: 1261246 (C4 (Web Text))

Max Activating Token Index: 469

Text #8

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.0301. Min Act: -0.0000

Data Index: 291385 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.0126. Min Act: -0.0000

Data Index: 1074154 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.0153. Min Act: -0.0000

Data Index: 82067 (C4 (Web Text))

Max Activating Token Index: 680

Text #11

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.0167. Min Act: -0.0000

Data Index: 306309 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.0108. Min Act: -0.0000

Data Index: 339967 (C4 (Web Text))

Max Activating Token Index: 1007

Text #13

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.0114. Min Act: -0.0000

Data Index: 233861 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.0116. Min Act: -0.0000

Data Index: 722012 (C4 (Web Text))

Max Activating Token Index: 827

Text #15

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.0114. Min Act: -0.0000

Data Index: 100959 (C4 (Web Text))

Max Activating Token Index: 711

Text #16

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.0111. Min Act: -0.0000

Data Index: 518300 (C4 (Web Text))

Max Activating Token Index: 392

Text #17

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.0098. Min Act: -0.0000

Data Index: 793033 (C4 (Web Text))

Max Activating Token Index: 783

Text #18

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.0098. Min Act: -0.0000

Data Index: 1079872 (C4 (Web Text))

Max Activating Token Index: 798

Text #19

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.0098. Min Act: -0.0000

Data Index: 592267 (C4 (Web Text))

Max Activating Token Index: 308