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

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

Neuron 4517 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0157. Min Range: -1.0157

Max Act: 1.0157. Min Act: -0.0000

Data Index: 684543 (C4 (Web Text))

Max Activating Token Index: 697

Text #1

Max Range: 1.0157. Min Range: -1.0157

Max Act: 0.9845. Min Act: -0.0000

Data Index: 318384 (C4 (Web Text))

Max Activating Token Index: 989

Text #2

Max Range: 1.0157. Min Range: -1.0157

Max Act: 0.9650. Min Act: -0.0000

Data Index: 105441 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 1.0157. Min Range: -1.0157

Max Act: 0.8035. Min Act: -0.0000

Data Index: 484475 (C4 (Web Text))

Max Activating Token Index: 864

Text #4

Max Range: 1.0157. Min Range: -1.0157

Max Act: 0.8636. Min Act: -0.0000

Data Index: 747364 (C4 (Web Text))

Max Activating Token Index: 660

Text #5

Max Range: 1.0157. Min Range: -1.0157

Max Act: 0.8017. Min Act: -0.0000

Data Index: 662548 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 1.0157. Min Range: -1.0157

Max Act: 0.6752. Min Act: -0.0000

Data Index: 763222 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 1.0157. Min Range: -1.0157

Max Act: 0.7343. Min Act: -0.0000

Data Index: 598486 (C4 (Web Text))

Max Activating Token Index: 978

Text #8

Max Range: 1.0157. Min Range: -1.0157

Max Act: 0.7212. Min Act: -0.0000

Data Index: 578616 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 1.0157. Min Range: -1.0157

Max Act: 0.7334. Min Act: -0.0000

Data Index: 507476 (C4 (Web Text))

Max Activating Token Index: 351

Text #10

Max Range: 1.0157. Min Range: -1.0157

Max Act: 0.6982. Min Act: -0.0000

Data Index: 887285 (C4 (Web Text))

Max Activating Token Index: 329

Text #11

Max Range: 1.0157. Min Range: -1.0157

Max Act: 0.6734. Min Act: -0.0000

Data Index: 1104685 (C4 (Web Text))

Max Activating Token Index: 580

Text #12

Max Range: 1.0157. Min Range: -1.0157

Max Act: 0.6472. Min Act: -0.0000

Data Index: 161263 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 1.0157. Min Range: -1.0157

Max Act: 0.6332. Min Act: -0.0000

Data Index: 1050069 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 1.0157. Min Range: -1.0157

Max Act: 0.5922. Min Act: -0.0000

Data Index: 322213 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 1.0157. Min Range: -1.0157

Max Act: 0.5770. Min Act: -0.0000

Data Index: 812332 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 1.0157. Min Range: -1.0157

Max Act: 0.5641. Min Act: -0.0000

Data Index: 455502 (C4 (Web Text))

Max Activating Token Index: 914

Text #17

Max Range: 1.0157. Min Range: -1.0157

Max Act: 0.5620. Min Act: -0.0000

Data Index: 403194 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 1.0157. Min Range: -1.0157

Max Act: 0.5271. Min Act: -0.0000

Data Index: 605637 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 1.0157. Min Range: -1.0157

Max Act: 0.5159. Min Act: -0.0000

Data Index: 1000149 (C4 (Web Text))

Max Activating Token Index: 439