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

Dataset: The Pile

Neuron 780 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0115. Min Range: -1.0115

Max Act: 1.0115. Min Act: -0.0000

Data Index: 1818905 (The Pile)

Max Activating Token Index: 318

Text #1

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.9444. Min Act: -0.0000

Data Index: 768077 (The Pile)

Max Activating Token Index: 235

Text #2

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.9180. Min Act: -0.0000

Data Index: 578544 (The Pile)

Max Activating Token Index: 617

Text #3

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.9227. Min Act: -0.0000

Data Index: 276523 (The Pile)

Max Activating Token Index: 260

Text #4

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.9008. Min Act: -0.0000

Data Index: 583999 (The Pile)

Max Activating Token Index: 162

Text #5

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.8234. Min Act: -0.0000

Data Index: 679249 (The Pile)

Max Activating Token Index: 50

Text #6

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.7533. Min Act: -0.0000

Data Index: 1521093 (The Pile)

Max Activating Token Index: 817

Text #7

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.6172. Min Act: -0.0000

Data Index: 284723 (The Pile)

Max Activating Token Index: 962

Text #8

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.5915. Min Act: -0.0000

Data Index: 375887 (The Pile)

Max Activating Token Index: 776

Text #9

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.5884. Min Act: -0.0000

Data Index: 1181325 (The Pile)

Max Activating Token Index: 90

Text #10

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.6040. Min Act: -0.0000

Data Index: 1966836 (The Pile)

Max Activating Token Index: 76

Text #11

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.5491. Min Act: -0.0000

Data Index: 1504055 (The Pile)

Max Activating Token Index: 419

Text #12

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.5679. Min Act: -0.0000

Data Index: 852671 (The Pile)

Max Activating Token Index: 990

Text #13

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.5385. Min Act: -0.0000

Data Index: 1105416 (The Pile)

Max Activating Token Index: 1000

Text #14

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.5182. Min Act: -0.0000

Data Index: 891917 (The Pile)

Max Activating Token Index: 969

Text #15

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.5182. Min Act: -0.0000

Data Index: 602743 (The Pile)

Max Activating Token Index: 57

Text #16

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.4605. Min Act: -0.0000

Data Index: 327614 (The Pile)

Max Activating Token Index: 325

Text #17

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.4415. Min Act: -0.0000

Data Index: 1664436 (The Pile)

Max Activating Token Index: 318

Text #18

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.4645. Min Act: -0.0000

Data Index: 901244 (The Pile)

Max Activating Token Index: 515

Text #19

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.4621. Min Act: -0.0000

Data Index: 833267 (The Pile)

Max Activating Token Index: 192