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

Dataset: The Pile

Neuron 2540 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5771. Min Range: -1.5771

Max Act: 1.4442. Min Act: -0.0000

Data Index: 1238922 (The Pile)

Max Activating Token Index: 327

Text #1

Max Range: 1.5771. Min Range: -1.5771

Max Act: 1.4701. Min Act: -0.0000

Data Index: 99850 (The Pile)

Max Activating Token Index: 307

Text #2

Max Range: 1.5771. Min Range: -1.5771

Max Act: 1.4825. Min Act: -0.0000

Data Index: 1277097 (The Pile)

Max Activating Token Index: 757

Text #3

Max Range: 1.5771. Min Range: -1.5771

Max Act: 1.5771. Min Act: -0.0000

Data Index: 310451 (The Pile)

Max Activating Token Index: 580

Text #4

Max Range: 1.5771. Min Range: -1.5771

Max Act: 1.3932. Min Act: -0.0000

Data Index: 386194 (The Pile)

Max Activating Token Index: 53

Text #5

Max Range: 1.5771. Min Range: -1.5771

Max Act: 1.2858. Min Act: -0.0000

Data Index: 1697728 (The Pile)

Max Activating Token Index: 305

Text #6

Max Range: 1.5771. Min Range: -1.5771

Max Act: 1.3381. Min Act: -0.0000

Data Index: 397959 (The Pile)

Max Activating Token Index: 605

Text #7

Max Range: 1.5771. Min Range: -1.5771

Max Act: 1.3791. Min Act: -0.0000

Data Index: 583974 (The Pile)

Max Activating Token Index: 113

Text #8

Max Range: 1.5771. Min Range: -1.5771

Max Act: 1.2286. Min Act: -0.0000

Data Index: 1699479 (The Pile)

Max Activating Token Index: 118

Text #9

Max Range: 1.5771. Min Range: -1.5771

Max Act: 1.4043. Min Act: -0.0000

Data Index: 1806547 (The Pile)

Max Activating Token Index: 503

Text #10

Max Range: 1.5771. Min Range: -1.5771

Max Act: 1.4356. Min Act: -0.0000

Data Index: 137855 (The Pile)

Max Activating Token Index: 858

Text #11

Max Range: 1.5771. Min Range: -1.5771

Max Act: 1.3007. Min Act: -0.0000

Data Index: 1364730 (The Pile)

Max Activating Token Index: 530

Text #12

Max Range: 1.5771. Min Range: -1.5771

Max Act: 1.2813. Min Act: -0.0000

Data Index: 1726206 (The Pile)

Max Activating Token Index: 101

Text #13

Max Range: 1.5771. Min Range: -1.5771

Max Act: 1.2278. Min Act: -0.0000

Data Index: 24498 (The Pile)

Max Activating Token Index: 924

Text #14

Max Range: 1.5771. Min Range: -1.5771

Max Act: 1.1699. Min Act: -0.0000

Data Index: 546574 (The Pile)

Max Activating Token Index: 171

Text #15

Max Range: 1.5771. Min Range: -1.5771

Max Act: 1.3358. Min Act: -0.0000

Data Index: 193063 (The Pile)

Max Activating Token Index: 378

Text #16

Max Range: 1.5771. Min Range: -1.5771

Max Act: 1.2310. Min Act: -0.0000

Data Index: 531305 (The Pile)

Max Activating Token Index: 312

Text #17

Max Range: 1.5771. Min Range: -1.5771

Max Act: 1.0867. Min Act: -0.0000

Data Index: 1690580 (The Pile)

Max Activating Token Index: 141

Text #18

Max Range: 1.5771. Min Range: -1.5771

Max Act: 1.2160. Min Act: -0.0000

Data Index: 649459 (The Pile)

Max Activating Token Index: 467

Text #19

Max Range: 1.5771. Min Range: -1.5771

Max Act: 1.2439. Min Act: -0.0000

Data Index: 1554977 (The Pile)

Max Activating Token Index: 442