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

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

Neuron 1207 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0189. Min Act: -0.0003

Data Index: 96390 (C4 (Web Text))

Max Activating Token Index: 1

Text #1

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0189. Min Act: -0.0003

Data Index: 23327 (C4 (Web Text))

Max Activating Token Index: 1

Text #2

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0189. Min Act: -0.0003

Data Index: 179414 (C4 (Web Text))

Max Activating Token Index: 1

Text #3

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0189. Min Act: -0.0003

Data Index: 183565 (C4 (Web Text))

Max Activating Token Index: 1

Text #4

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0189. Min Act: -0.0003

Data Index: 167743 (C4 (Web Text))

Max Activating Token Index: 1

Text #5

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0189. Min Act: -0.0003

Data Index: 11375 (C4 (Web Text))

Max Activating Token Index: 1

Text #6

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0189. Min Act: -0.0003

Data Index: 152666 (C4 (Web Text))

Max Activating Token Index: 1

Text #7

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0189. Min Act: -0.0003

Data Index: 211233 (C4 (Web Text))

Max Activating Token Index: 1

Text #8

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0189. Min Act: -0.0003

Data Index: 141744 (C4 (Web Text))

Max Activating Token Index: 1

Text #9

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0189. Min Act: -0.0003

Data Index: 164378 (C4 (Web Text))

Max Activating Token Index: 1

Text #10

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0189. Min Act: -0.0003

Data Index: 212225 (C4 (Web Text))

Max Activating Token Index: 1

Text #11

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0189. Min Act: -0.0003

Data Index: 237551 (C4 (Web Text))

Max Activating Token Index: 1

Text #12

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0189. Min Act: -0.0003

Data Index: 267020 (C4 (Web Text))

Max Activating Token Index: 1

Text #13

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0189. Min Act: -0.0003

Data Index: 270267 (C4 (Web Text))

Max Activating Token Index: 1

Text #14

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0189. Min Act: -0.0003

Data Index: 95215 (C4 (Web Text))

Max Activating Token Index: 1

Text #15

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0189. Min Act: -0.0003

Data Index: 48611 (C4 (Web Text))

Max Activating Token Index: 1

Text #16

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0189. Min Act: -0.0003

Data Index: 272334 (C4 (Web Text))

Max Activating Token Index: 1

Text #17

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0189. Min Act: -0.0003

Data Index: 39443 (C4 (Web Text))

Max Activating Token Index: 1

Text #18

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0189. Min Act: -0.0003

Data Index: 376334 (C4 (Web Text))

Max Activating Token Index: 1

Text #19

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0189. Min Act: -0.0003

Data Index: 72840 (C4 (Web Text))

Max Activating Token Index: 1