Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3001 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.5273. Min Act: -0.0000

Data Index: 191535 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.4896. Min Act: -0.0001

Data Index: 529228 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.4821. Min Act: -0.0001

Data Index: 1192357 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.4902. Min Act: -0.0000

Data Index: 962305 (C4 (Web Text))

Max Activating Token Index: 483

Text #4

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.5049. Min Act: -0.0000

Data Index: 906372 (C4 (Web Text))

Max Activating Token Index: 73

Text #5

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.4741. Min Act: -0.0001

Data Index: 112937 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.4594. Min Act: -0.0000

Data Index: 1205749 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.4768. Min Act: -0.0001

Data Index: 877056 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.4599. Min Act: -0.0001

Data Index: 749276 (C4 (Web Text))

Max Activating Token Index: 627

Text #9

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.4248. Min Act: -0.0001

Data Index: 504611 (C4 (Web Text))

Max Activating Token Index: 526

Text #10

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.4625. Min Act: -0.0000

Data Index: 1027900 (C4 (Web Text))

Max Activating Token Index: 722

Text #11

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.4440. Min Act: -0.0000

Data Index: 164985 (C4 (Web Text))

Max Activating Token Index: 937

Text #12

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.4469. Min Act: -0.0001

Data Index: 981511 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.4432. Min Act: -0.0000

Data Index: 179872 (C4 (Web Text))

Max Activating Token Index: 264

Text #14

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.3997. Min Act: -0.0000

Data Index: 528061 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.4310. Min Act: -0.0001

Data Index: 407183 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.4337. Min Act: -0.0001

Data Index: 176577 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.4153. Min Act: -0.0000

Data Index: 1132663 (C4 (Web Text))

Max Activating Token Index: 591

Text #18

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.4603. Min Act: -0.0000

Data Index: 1163913 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.4290. Min Act: -0.0001

Data Index: 563113 (C4 (Web Text))

Max Activating Token Index: 426