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

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

Neuron 2426 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: 8.2216. Min Range: -8.2216

Max Act: 8.2216. Min Act: -0.0000

Data Index: 492048 (C4 (Web Text))

Max Activating Token Index: 184

Text #1

Max Range: 8.2216. Min Range: -8.2216

Max Act: 7.9712. Min Act: -0.0000

Data Index: 1156122 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 8.2216. Min Range: -8.2216

Max Act: 7.6107. Min Act: -0.0000

Data Index: 489397 (C4 (Web Text))

Max Activating Token Index: 473

Text #3

Max Range: 8.2216. Min Range: -8.2216

Max Act: 7.7045. Min Act: -0.0000

Data Index: 1180806 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 8.2216. Min Range: -8.2216

Max Act: 7.7154. Min Act: -0.0000

Data Index: 224525 (C4 (Web Text))

Max Activating Token Index: 367

Text #5

Max Range: 8.2216. Min Range: -8.2216

Max Act: 7.6635. Min Act: -0.0000

Data Index: 568165 (C4 (Web Text))

Max Activating Token Index: 291

Text #6

Max Range: 8.2216. Min Range: -8.2216

Max Act: 7.6843. Min Act: -0.0000

Data Index: 606204 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 8.2216. Min Range: -8.2216

Max Act: 7.4525. Min Act: -0.0000

Data Index: 1244039 (C4 (Web Text))

Max Activating Token Index: 480

Text #8

Max Range: 8.2216. Min Range: -8.2216

Max Act: 7.6430. Min Act: -0.0000

Data Index: 1110853 (C4 (Web Text))

Max Activating Token Index: 533

Text #9

Max Range: 8.2216. Min Range: -8.2216

Max Act: 7.4622. Min Act: -0.0000

Data Index: 1322156 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 8.2216. Min Range: -8.2216

Max Act: 7.6183. Min Act: -0.0000

Data Index: 1058937 (C4 (Web Text))

Max Activating Token Index: 618

Text #11

Max Range: 8.2216. Min Range: -8.2216

Max Act: 7.6308. Min Act: -0.0000

Data Index: 1073692 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 8.2216. Min Range: -8.2216

Max Act: 7.4411. Min Act: -0.0000

Data Index: 783274 (C4 (Web Text))

Max Activating Token Index: 534

Text #13

Max Range: 8.2216. Min Range: -8.2216

Max Act: 7.5988. Min Act: -0.0000

Data Index: 1244088 (C4 (Web Text))

Max Activating Token Index: 781

Text #14

Max Range: 8.2216. Min Range: -8.2216

Max Act: 7.4354. Min Act: -0.0000

Data Index: 15055 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 8.2216. Min Range: -8.2216

Max Act: 7.6145. Min Act: -0.0000

Data Index: 484735 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 8.2216. Min Range: -8.2216

Max Act: 7.4234. Min Act: -0.0000

Data Index: 1210237 (C4 (Web Text))

Max Activating Token Index: 318

Text #17

Max Range: 8.2216. Min Range: -8.2216

Max Act: 7.6079. Min Act: -0.0000

Data Index: 536501 (C4 (Web Text))

Max Activating Token Index: 883

Text #18

Max Range: 8.2216. Min Range: -8.2216

Max Act: 7.3879. Min Act: -0.0000

Data Index: 704736 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 8.2216. Min Range: -8.2216

Max Act: 7.7064. Min Act: -0.0000

Data Index: 1104353 (C4 (Web Text))

Max Activating Token Index: 88