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

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

Neuron 1828 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1292. Min Range: -1.1292

Max Act: 1.1292. Min Act: -0.0000

Data Index: 222918 (C4 (Web Text))

Max Activating Token Index: 106

Text #1

Max Range: 1.1292. Min Range: -1.1292

Max Act: 1.1127. Min Act: -0.0000

Data Index: 397623 (C4 (Web Text))

Max Activating Token Index: 181

Text #2

Max Range: 1.1292. Min Range: -1.1292

Max Act: 1.0365. Min Act: -0.0000

Data Index: 922700 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.9492. Min Act: -0.0000

Data Index: 664156 (C4 (Web Text))

Max Activating Token Index: 451

Text #4

Max Range: 1.1292. Min Range: -1.1292

Max Act: 1.0283. Min Act: -0.0000

Data Index: 132752 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.9799. Min Act: -0.0000

Data Index: 1128691 (C4 (Web Text))

Max Activating Token Index: 246

Text #6

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.9102. Min Act: -0.0000

Data Index: 245847 (C4 (Web Text))

Max Activating Token Index: 446

Text #7

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.9180. Min Act: -0.0000

Data Index: 191371 (C4 (Web Text))

Max Activating Token Index: 853

Text #8

Max Range: 1.1292. Min Range: -1.1292

Max Act: 1.0105. Min Act: -0.0000

Data Index: 508723 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.8288. Min Act: -0.0000

Data Index: 686550 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.8853. Min Act: -0.0000

Data Index: 391533 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.9021. Min Act: -0.0000

Data Index: 54392 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.9099. Min Act: -0.0000

Data Index: 1214446 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.8607. Min Act: -0.0000

Data Index: 264128 (C4 (Web Text))

Max Activating Token Index: 805

Text #14

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.9668. Min Act: -0.0000

Data Index: 1124846 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.8411. Min Act: -0.0000

Data Index: 1276596 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.8683. Min Act: -0.0000

Data Index: 650365 (C4 (Web Text))

Max Activating Token Index: 946

Text #17

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.8518. Min Act: -0.0000

Data Index: 333786 (C4 (Web Text))

Max Activating Token Index: 466

Text #18

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.8757. Min Act: -0.0000

Data Index: 873511 (C4 (Web Text))

Max Activating Token Index: 988

Text #19

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.7801. Min Act: -0.0000

Data Index: 626068 (C4 (Web Text))

Max Activating Token Index: 773