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

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

Neuron 4031 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0599. Min Act: -0.0002

Data Index: 294561 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0584. Min Act: -0.0002

Data Index: 1147640 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0515. Min Act: -0.0002

Data Index: 357818 (C4 (Web Text))

Max Activating Token Index: 452

Text #3

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0506. Min Act: -0.0002

Data Index: 312664 (C4 (Web Text))

Max Activating Token Index: 672

Text #4

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0482. Min Act: -0.0002

Data Index: 814085 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0428. Min Act: -0.0001

Data Index: 418215 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0411. Min Act: -0.0001

Data Index: 446275 (C4 (Web Text))

Max Activating Token Index: 111

Text #7

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0407. Min Act: -0.0002

Data Index: 832889 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0406. Min Act: -0.0002

Data Index: 1312657 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0383. Min Act: -0.0001

Data Index: 1308631 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0381. Min Act: -0.0002

Data Index: 751569 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0381. Min Act: -0.0001

Data Index: 211385 (C4 (Web Text))

Max Activating Token Index: 740

Text #12

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0413. Min Act: -0.0001

Data Index: 1342794 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0393. Min Act: -0.0001

Data Index: 485157 (C4 (Web Text))

Max Activating Token Index: 277

Text #14

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0395. Min Act: -0.0002

Data Index: 1269073 (C4 (Web Text))

Max Activating Token Index: 149

Text #15

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0366. Min Act: -0.0001

Data Index: 525654 (C4 (Web Text))

Max Activating Token Index: 128

Text #16

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0379. Min Act: -0.0002

Data Index: 266301 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0390. Min Act: -0.0001

Data Index: 312761 (C4 (Web Text))

Max Activating Token Index: 119

Text #18

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0376. Min Act: -0.0002

Data Index: 948264 (C4 (Web Text))

Max Activating Token Index: 255

Text #19

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0389. Min Act: -0.0001

Data Index: 1192815 (C4 (Web Text))

Max Activating Token Index: 284