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

Dataset: The Pile

Neuron 290 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: 0.9520. Min Range: -0.9520

Max Act: 0.9520. Min Act: -0.0000

Data Index: 755342 (The Pile)

Max Activating Token Index: 953

Text #1

Max Range: 0.9520. Min Range: -0.9520

Max Act: 0.8638. Min Act: -0.0000

Data Index: 1512349 (The Pile)

Max Activating Token Index: 411

Text #2

Max Range: 0.9520. Min Range: -0.9520

Max Act: 0.8952. Min Act: -0.0000

Data Index: 907307 (The Pile)

Max Activating Token Index: 39

Text #3

Max Range: 0.9520. Min Range: -0.9520

Max Act: 0.9482. Min Act: -0.0000

Data Index: 499830 (The Pile)

Max Activating Token Index: 614

Text #4

Max Range: 0.9520. Min Range: -0.9520

Max Act: 0.8167. Min Act: -0.0000

Data Index: 1813147 (The Pile)

Max Activating Token Index: 15

Text #5

Max Range: 0.9520. Min Range: -0.9520

Max Act: 0.8824. Min Act: -0.0000

Data Index: 1295578 (The Pile)

Max Activating Token Index: 76

Text #6

Max Range: 0.9520. Min Range: -0.9520

Max Act: 0.7754. Min Act: -0.0000

Data Index: 396476 (The Pile)

Max Activating Token Index: 1014

Text #7

Max Range: 0.9520. Min Range: -0.9520

Max Act: 0.7858. Min Act: -0.0000

Data Index: 461688 (The Pile)

Max Activating Token Index: 799

Text #8

Max Range: 0.9520. Min Range: -0.9520

Max Act: 0.7231. Min Act: -0.0000

Data Index: 1979134 (The Pile)

Max Activating Token Index: 437

Text #9

Max Range: 0.9520. Min Range: -0.9520

Max Act: 0.7278. Min Act: -0.0000

Data Index: 507757 (The Pile)

Max Activating Token Index: 426

Text #10

Max Range: 0.9520. Min Range: -0.9520

Max Act: 0.6433. Min Act: -0.0000

Data Index: 810860 (The Pile)

Max Activating Token Index: 1006

Text #11

Max Range: 0.9520. Min Range: -0.9520

Max Act: 0.7212. Min Act: -0.0000

Data Index: 654937 (The Pile)

Max Activating Token Index: 133

Text #12

Max Range: 0.9520. Min Range: -0.9520

Max Act: 0.6875. Min Act: -0.0000

Data Index: 1014436 (The Pile)

Max Activating Token Index: 31

Text #13

Max Range: 0.9520. Min Range: -0.9520

Max Act: 0.7285. Min Act: -0.0000

Data Index: 1789523 (The Pile)

Max Activating Token Index: 562

Text #14

Max Range: 0.9520. Min Range: -0.9520

Max Act: 0.6787. Min Act: -0.0000

Data Index: 518113 (The Pile)

Max Activating Token Index: 793

Text #15

Max Range: 0.9520. Min Range: -0.9520

Max Act: 0.6649. Min Act: -0.0000

Data Index: 1627448 (The Pile)

Max Activating Token Index: 436

Text #16

Max Range: 0.9520. Min Range: -0.9520

Max Act: 0.6417. Min Act: -0.0000

Data Index: 1650590 (The Pile)

Max Activating Token Index: 378

Text #17

Max Range: 0.9520. Min Range: -0.9520

Max Act: 0.7363. Min Act: -0.0000

Data Index: 1530992 (The Pile)

Max Activating Token Index: 34

Text #18

Max Range: 0.9520. Min Range: -0.9520

Max Act: 0.7024. Min Act: -0.0000

Data Index: 1980120 (The Pile)

Max Activating Token Index: 236

Text #19

Max Range: 0.9520. Min Range: -0.9520

Max Act: 0.6106. Min Act: -0.0000

Data Index: 643143 (The Pile)

Max Activating Token Index: 561