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

Dataset: The Pile

Neuron 3277 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.9232. Min Act: -0.0000

Data Index: 183407 (The Pile)

Max Activating Token Index: 317

Text #1

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.6509. Min Act: -0.0000

Data Index: 1331069 (The Pile)

Max Activating Token Index: 894

Text #2

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.5703. Min Act: -0.0000

Data Index: 122227 (The Pile)

Max Activating Token Index: 39

Text #3

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.6192. Min Act: -0.0000

Data Index: 985175 (The Pile)

Max Activating Token Index: 393

Text #4

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.5737. Min Act: -0.0000

Data Index: 48054 (The Pile)

Max Activating Token Index: 391

Text #5

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.6059. Min Act: -0.0000

Data Index: 138664 (The Pile)

Max Activating Token Index: 1020

Text #6

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.5825. Min Act: -0.0000

Data Index: 1886774 (The Pile)

Max Activating Token Index: 663

Text #7

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.4802. Min Act: -0.0000

Data Index: 238435 (The Pile)

Max Activating Token Index: 969

Text #8

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.5206. Min Act: -0.0000

Data Index: 1251426 (The Pile)

Max Activating Token Index: 849

Text #9

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.5011. Min Act: -0.0000

Data Index: 62594 (The Pile)

Max Activating Token Index: 176

Text #10

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.5169. Min Act: -0.0000

Data Index: 311808 (The Pile)

Max Activating Token Index: 60

Text #11

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.4164. Min Act: -0.0000

Data Index: 668629 (The Pile)

Max Activating Token Index: 583

Text #12

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.4576. Min Act: -0.0000

Data Index: 1509455 (The Pile)

Max Activating Token Index: 765

Text #13

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.4976. Min Act: -0.0000

Data Index: 1972030 (The Pile)

Max Activating Token Index: 59

Text #14

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.4784. Min Act: -0.0000

Data Index: 781923 (The Pile)

Max Activating Token Index: 514

Text #15

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.4953. Min Act: -0.0000

Data Index: 1356042 (The Pile)

Max Activating Token Index: 676

Text #16

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.4785. Min Act: -0.0000

Data Index: 353992 (The Pile)

Max Activating Token Index: 668

Text #17

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.5066. Min Act: -0.0000

Data Index: 1680466 (The Pile)

Max Activating Token Index: 470

Text #18

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.4564. Min Act: -0.0000

Data Index: 385328 (The Pile)

Max Activating Token Index: 612

Text #19

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.4710. Min Act: -0.0000

Data Index: 1104054 (The Pile)

Max Activating Token Index: 186