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

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

Neuron 5051 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8336. Min Range: -1.8336

Max Act: 1.8239. Min Act: -0.0000

Data Index: 805326 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 1.8336. Min Range: -1.8336

Max Act: 1.8336. Min Act: -0.0000

Data Index: 690593 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 1.8336. Min Range: -1.8336

Max Act: 1.4405. Min Act: -0.0000

Data Index: 1201699 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 1.8336. Min Range: -1.8336

Max Act: 1.4423. Min Act: -0.0000

Data Index: 1250404 (C4 (Web Text))

Max Activating Token Index: 845

Text #4

Max Range: 1.8336. Min Range: -1.8336

Max Act: 1.3451. Min Act: -0.0000

Data Index: 1279493 (C4 (Web Text))

Max Activating Token Index: 713

Text #5

Max Range: 1.8336. Min Range: -1.8336

Max Act: 1.3363. Min Act: -0.0000

Data Index: 592517 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 1.8336. Min Range: -1.8336

Max Act: 1.3262. Min Act: -0.0000

Data Index: 893552 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 1.8336. Min Range: -1.8336

Max Act: 1.2538. Min Act: -0.0000

Data Index: 536127 (C4 (Web Text))

Max Activating Token Index: 905

Text #8

Max Range: 1.8336. Min Range: -1.8336

Max Act: 1.2797. Min Act: -0.0000

Data Index: 377866 (C4 (Web Text))

Max Activating Token Index: 754

Text #9

Max Range: 1.8336. Min Range: -1.8336

Max Act: 1.2108. Min Act: -0.0000

Data Index: 1072124 (C4 (Web Text))

Max Activating Token Index: 513

Text #10

Max Range: 1.8336. Min Range: -1.8336

Max Act: 1.2158. Min Act: -0.0000

Data Index: 1279375 (C4 (Web Text))

Max Activating Token Index: 329

Text #11

Max Range: 1.8336. Min Range: -1.8336

Max Act: 1.1771. Min Act: -0.0000

Data Index: 403081 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 1.8336. Min Range: -1.8336

Max Act: 1.1620. Min Act: -0.0000

Data Index: 504595 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 1.8336. Min Range: -1.8336

Max Act: 1.2274. Min Act: -0.0000

Data Index: 479072 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 1.8336. Min Range: -1.8336

Max Act: 1.1813. Min Act: -0.0000

Data Index: 318862 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 1.8336. Min Range: -1.8336

Max Act: 1.1768. Min Act: -0.0000

Data Index: 1071468 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 1.8336. Min Range: -1.8336

Max Act: 1.1805. Min Act: -0.0000

Data Index: 1031122 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 1.8336. Min Range: -1.8336

Max Act: 1.2479. Min Act: -0.0000

Data Index: 811770 (C4 (Web Text))

Max Activating Token Index: 613

Text #18

Max Range: 1.8336. Min Range: -1.8336

Max Act: 1.1575. Min Act: -0.0000

Data Index: 882458 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 1.8336. Min Range: -1.8336

Max Act: 1.1461. Min Act: -0.0000

Data Index: 456276 (C4 (Web Text))

Max Activating Token Index: 133