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

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

Neuron 3918 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: 0.7678. Min Range: -0.7678

Max Act: 0.7678. Min Act: -0.0000

Data Index: 99272 (C4 (Web Text))

Max Activating Token Index: 828

Text #1

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.7510. Min Act: -0.0000

Data Index: 889484 (C4 (Web Text))

Max Activating Token Index: 197

Text #2

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.6663. Min Act: -0.0000

Data Index: 985122 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.5742. Min Act: -0.0000

Data Index: 1073869 (C4 (Web Text))

Max Activating Token Index: 339

Text #4

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.5646. Min Act: -0.0000

Data Index: 227287 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.5713. Min Act: -0.0000

Data Index: 327838 (C4 (Web Text))

Max Activating Token Index: 129

Text #6

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.5239. Min Act: -0.0000

Data Index: 788598 (C4 (Web Text))

Max Activating Token Index: 598

Text #7

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.5118. Min Act: -0.0000

Data Index: 317731 (C4 (Web Text))

Max Activating Token Index: 838

Text #8

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.4926. Min Act: -0.0000

Data Index: 786513 (C4 (Web Text))

Max Activating Token Index: 315

Text #9

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.4646. Min Act: -0.0000

Data Index: 839816 (C4 (Web Text))

Max Activating Token Index: 253

Text #10

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.4351. Min Act: -0.0000

Data Index: 330087 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.4610. Min Act: -0.0000

Data Index: 846149 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.4729. Min Act: -0.0000

Data Index: 427199 (C4 (Web Text))

Max Activating Token Index: 851

Text #13

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.4431. Min Act: -0.0000

Data Index: 509473 (C4 (Web Text))

Max Activating Token Index: 367

Text #14

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.4275. Min Act: -0.0000

Data Index: 1005576 (C4 (Web Text))

Max Activating Token Index: 411

Text #15

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.4092. Min Act: -0.0000

Data Index: 6753 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.4315. Min Act: -0.0000

Data Index: 132947 (C4 (Web Text))

Max Activating Token Index: 632

Text #17

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.4244. Min Act: -0.0000

Data Index: 311768 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.4071. Min Act: -0.0000

Data Index: 989075 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.4150. Min Act: -0.0000

Data Index: 944014 (C4 (Web Text))

Max Activating Token Index: 78