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

Dataset: The Pile

Neuron 3772 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4524. Min Range: -1.4524

Max Act: 1.4524. Min Act: -0.0000

Data Index: 1332560 (The Pile)

Max Activating Token Index: 558

Text #1

Max Range: 1.4524. Min Range: -1.4524

Max Act: 1.2892. Min Act: -0.0000

Data Index: 366696 (The Pile)

Max Activating Token Index: 883

Text #2

Max Range: 1.4524. Min Range: -1.4524

Max Act: 1.1223. Min Act: -0.0000

Data Index: 1724254 (The Pile)

Max Activating Token Index: 92

Text #3

Max Range: 1.4524. Min Range: -1.4524

Max Act: 1.2266. Min Act: -0.0000

Data Index: 1873542 (The Pile)

Max Activating Token Index: 302

Text #4

Max Range: 1.4524. Min Range: -1.4524

Max Act: 1.0743. Min Act: 0.0000

Data Index: 1892594 (The Pile)

Max Activating Token Index: 17

Text #5

Max Range: 1.4524. Min Range: -1.4524

Max Act: 1.0522. Min Act: -0.0000

Data Index: 801494 (The Pile)

Max Activating Token Index: 401

Text #6

Max Range: 1.4524. Min Range: -1.4524

Max Act: 1.1031. Min Act: -0.0000

Data Index: 1312927 (The Pile)

Max Activating Token Index: 183

Text #7

Max Range: 1.4524. Min Range: -1.4524

Max Act: 0.9126. Min Act: -0.0000

Data Index: 792155 (The Pile)

Max Activating Token Index: 643

Text #8

Max Range: 1.4524. Min Range: -1.4524

Max Act: 1.0003. Min Act: -0.0000

Data Index: 105747 (The Pile)

Max Activating Token Index: 623

Text #9

Max Range: 1.4524. Min Range: -1.4524

Max Act: 1.0529. Min Act: -0.0000

Data Index: 744783 (The Pile)

Max Activating Token Index: 244

Text #10

Max Range: 1.4524. Min Range: -1.4524

Max Act: 1.0216. Min Act: -0.0000

Data Index: 1949596 (The Pile)

Max Activating Token Index: 114

Text #11

Max Range: 1.4524. Min Range: -1.4524

Max Act: 1.0176. Min Act: -0.0000

Data Index: 1390922 (The Pile)

Max Activating Token Index: 302

Text #12

Max Range: 1.4524. Min Range: -1.4524

Max Act: 1.0268. Min Act: -0.0000

Data Index: 1464601 (The Pile)

Max Activating Token Index: 365

Text #13

Max Range: 1.4524. Min Range: -1.4524

Max Act: 0.9352. Min Act: -0.0000

Data Index: 1729218 (The Pile)

Max Activating Token Index: 741

Text #14

Max Range: 1.4524. Min Range: -1.4524

Max Act: 0.9399. Min Act: -0.0000

Data Index: 1224114 (The Pile)

Max Activating Token Index: 37

Text #15

Max Range: 1.4524. Min Range: -1.4524

Max Act: 0.8800. Min Act: -0.0000

Data Index: 405501 (The Pile)

Max Activating Token Index: 599

Text #16

Max Range: 1.4524. Min Range: -1.4524

Max Act: 0.9258. Min Act: -0.0000

Data Index: 1995368 (The Pile)

Max Activating Token Index: 741

Text #17

Max Range: 1.4524. Min Range: -1.4524

Max Act: 0.9497. Min Act: -0.0000

Data Index: 1406348 (The Pile)

Max Activating Token Index: 501

Text #18

Max Range: 1.4524. Min Range: -1.4524

Max Act: 0.9187. Min Act: -0.0000

Data Index: 11676 (The Pile)

Max Activating Token Index: 281

Text #19

Max Range: 1.4524. Min Range: -1.4524

Max Act: 0.8790. Min Act: -0.0000

Data Index: 621342 (The Pile)

Max Activating Token Index: 849