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

Dataset: The Pile

Neuron 1731 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.6336. Min Act: -0.0000

Data Index: 1315244 (The Pile)

Max Activating Token Index: 189

Text #1

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.5156. Min Act: -0.0000

Data Index: 112928 (The Pile)

Max Activating Token Index: 69

Text #2

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.5028. Min Act: -0.0000

Data Index: 1967752 (The Pile)

Max Activating Token Index: 17

Text #3

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.4990. Min Act: -0.0000

Data Index: 935779 (The Pile)

Max Activating Token Index: 474

Text #4

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.4606. Min Act: -0.0000

Data Index: 25733 (The Pile)

Max Activating Token Index: 1022

Text #5

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.4714. Min Act: -0.0000

Data Index: 721281 (The Pile)

Max Activating Token Index: 498

Text #6

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.4663. Min Act: -0.0000

Data Index: 820799 (The Pile)

Max Activating Token Index: 955

Text #7

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.4635. Min Act: -0.0000

Data Index: 1552696 (The Pile)

Max Activating Token Index: 643

Text #8

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.4608. Min Act: -0.0000

Data Index: 1192746 (The Pile)

Max Activating Token Index: 708

Text #9

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.4570. Min Act: -0.0000

Data Index: 1400730 (The Pile)

Max Activating Token Index: 427

Text #10

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.4856. Min Act: -0.0000

Data Index: 553889 (The Pile)

Max Activating Token Index: 216

Text #11

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.4397. Min Act: -0.0000

Data Index: 1638251 (The Pile)

Max Activating Token Index: 97

Text #12

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.4430. Min Act: -0.0000

Data Index: 994741 (The Pile)

Max Activating Token Index: 244

Text #13

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.4420. Min Act: -0.0000

Data Index: 1190884 (The Pile)

Max Activating Token Index: 622

Text #14

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.4381. Min Act: -0.0000

Data Index: 10337 (The Pile)

Max Activating Token Index: 967

Text #15

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.4228. Min Act: -0.0000

Data Index: 506593 (The Pile)

Max Activating Token Index: 135

Text #16

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.4321. Min Act: -0.0000

Data Index: 1661561 (The Pile)

Max Activating Token Index: 362

Text #17

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.4465. Min Act: -0.0000

Data Index: 39295 (The Pile)

Max Activating Token Index: 88

Text #18

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.4167. Min Act: -0.0000

Data Index: 1331561 (The Pile)

Max Activating Token Index: 598

Text #19

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.4379. Min Act: -0.0000

Data Index: 74114 (The Pile)

Max Activating Token Index: 415