Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4504 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2036. Min Range: -1.2036

Max Act: 1.2036. Min Act: -0.0003

Data Index: 1187592 (C4 (Web Text))

Max Activating Token Index: 525

Text #1

Max Range: 1.2036. Min Range: -1.2036

Max Act: 1.0055. Min Act: -0.0003

Data Index: 974096 (C4 (Web Text))

Max Activating Token Index: 246

Text #2

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.9684. Min Act: -0.0003

Data Index: 494229 (C4 (Web Text))

Max Activating Token Index: 999

Text #3

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.9608. Min Act: -0.0003

Data Index: 869114 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.9575. Min Act: -0.0003

Data Index: 742830 (C4 (Web Text))

Max Activating Token Index: 252

Text #5

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.9330. Min Act: -0.0003

Data Index: 689312 (C4 (Web Text))

Max Activating Token Index: 211

Text #6

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.9486. Min Act: -0.0003

Data Index: 1276146 (C4 (Web Text))

Max Activating Token Index: 279

Text #7

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.8659. Min Act: -0.0003

Data Index: 502162 (C4 (Web Text))

Max Activating Token Index: 253

Text #8

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.8817. Min Act: -0.0003

Data Index: 664457 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.8666. Min Act: -0.0002

Data Index: 1246530 (C4 (Web Text))

Max Activating Token Index: 337

Text #10

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.8489. Min Act: -0.0002

Data Index: 1101622 (C4 (Web Text))

Max Activating Token Index: 511

Text #11

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.8375. Min Act: -0.0003

Data Index: 694766 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.8356. Min Act: -0.0003

Data Index: 967608 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.8184. Min Act: -0.0003

Data Index: 769708 (C4 (Web Text))

Max Activating Token Index: 775

Text #14

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.8216. Min Act: -0.0003

Data Index: 368124 (C4 (Web Text))

Max Activating Token Index: 351

Text #15

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.7676. Min Act: -0.0003

Data Index: 643554 (C4 (Web Text))

Max Activating Token Index: 533

Text #16

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.8426. Min Act: -0.0003

Data Index: 92305 (C4 (Web Text))

Max Activating Token Index: 647

Text #17

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.8106. Min Act: -0.0003

Data Index: 40139 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.8126. Min Act: -0.0003

Data Index: 178051 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.7850. Min Act: -0.0002

Data Index: 676302 (C4 (Web Text))

Max Activating Token Index: 921