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

Dataset: The Pile

Neuron 295 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5619. Min Range: -0.5619

Max Act: 0.5619. Min Act: 0.0000

Data Index: 1509181 (The Pile)

Max Activating Token Index: 365

Text #1

Max Range: 0.5619. Min Range: -0.5619

Max Act: 0.5496. Min Act: -0.0000

Data Index: 1586507 (The Pile)

Max Activating Token Index: 423

Text #2

Max Range: 0.5619. Min Range: -0.5619

Max Act: 0.5451. Min Act: -0.0000

Data Index: 1985539 (The Pile)

Max Activating Token Index: 208

Text #3

Max Range: 0.5619. Min Range: -0.5619

Max Act: 0.5484. Min Act: -0.0000

Data Index: 734521 (The Pile)

Max Activating Token Index: 961

Text #4

Max Range: 0.5619. Min Range: -0.5619

Max Act: 0.5193. Min Act: -0.0000

Data Index: 498870 (The Pile)

Max Activating Token Index: 961

Text #5

Max Range: 0.5619. Min Range: -0.5619

Max Act: 0.4933. Min Act: -0.0000

Data Index: 121186 (The Pile)

Max Activating Token Index: 207

Text #6

Max Range: 0.5619. Min Range: -0.5619

Max Act: 0.4727. Min Act: -0.0000

Data Index: 1079121 (The Pile)

Max Activating Token Index: 638

Text #7

Max Range: 0.5619. Min Range: -0.5619

Max Act: 0.4823. Min Act: -0.0000

Data Index: 140669 (The Pile)

Max Activating Token Index: 166

Text #8

Max Range: 0.5619. Min Range: -0.5619

Max Act: 0.4762. Min Act: -0.0000

Data Index: 49159 (The Pile)

Max Activating Token Index: 476

Text #9

Max Range: 0.5619. Min Range: -0.5619

Max Act: 0.4779. Min Act: -0.0000

Data Index: 1213492 (The Pile)

Max Activating Token Index: 449

Text #10

Max Range: 0.5619. Min Range: -0.5619

Max Act: 0.4560. Min Act: -0.0000

Data Index: 606029 (The Pile)

Max Activating Token Index: 220

Text #11

Max Range: 0.5619. Min Range: -0.5619

Max Act: 0.4499. Min Act: -0.0000

Data Index: 610109 (The Pile)

Max Activating Token Index: 411

Text #12

Max Range: 0.5619. Min Range: -0.5619

Max Act: 0.4274. Min Act: -0.0000

Data Index: 1194443 (The Pile)

Max Activating Token Index: 132

Text #13

Max Range: 0.5619. Min Range: -0.5619

Max Act: 0.4141. Min Act: -0.0000

Data Index: 566867 (The Pile)

Max Activating Token Index: 885

Text #14

Max Range: 0.5619. Min Range: -0.5619

Max Act: 0.4142. Min Act: -0.0000

Data Index: 939093 (The Pile)

Max Activating Token Index: 60

Text #15

Max Range: 0.5619. Min Range: -0.5619

Max Act: 0.3981. Min Act: -0.0000

Data Index: 9965 (The Pile)

Max Activating Token Index: 284

Text #16

Max Range: 0.5619. Min Range: -0.5619

Max Act: 0.3817. Min Act: -0.0000

Data Index: 1642349 (The Pile)

Max Activating Token Index: 680

Text #17

Max Range: 0.5619. Min Range: -0.5619

Max Act: 0.4113. Min Act: -0.0000

Data Index: 328154 (The Pile)

Max Activating Token Index: 346

Text #18

Max Range: 0.5619. Min Range: -0.5619

Max Act: 0.4221. Min Act: -0.0000

Data Index: 859199 (The Pile)

Max Activating Token Index: 249

Text #19

Max Range: 0.5619. Min Range: -0.5619

Max Act: 0.4193. Min Act: -0.0000

Data Index: 1823539 (The Pile)

Max Activating Token Index: 420