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

Dataset: The Pile

Neuron 497 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: 0.6859. Min Range: -0.6859

Max Act: 0.6859. Min Act: -0.0000

Data Index: 322478 (The Pile)

Max Activating Token Index: 959

Text #1

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.6089. Min Act: -0.0000

Data Index: 1249190 (The Pile)

Max Activating Token Index: 613

Text #2

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.5940. Min Act: -0.0000

Data Index: 289086 (The Pile)

Max Activating Token Index: 267

Text #3

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.5356. Min Act: -0.0000

Data Index: 365993 (The Pile)

Max Activating Token Index: 344

Text #4

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.5351. Min Act: -0.0000

Data Index: 463091 (The Pile)

Max Activating Token Index: 930

Text #5

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.5435. Min Act: -0.0000

Data Index: 410309 (The Pile)

Max Activating Token Index: 64

Text #6

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.5338. Min Act: -0.0000

Data Index: 720316 (The Pile)

Max Activating Token Index: 778

Text #7

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.5421. Min Act: -0.0000

Data Index: 581346 (The Pile)

Max Activating Token Index: 960

Text #8

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.5338. Min Act: -0.0000

Data Index: 1890578 (The Pile)

Max Activating Token Index: 388

Text #9

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.4919. Min Act: -0.0000

Data Index: 395013 (The Pile)

Max Activating Token Index: 459

Text #10

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.5049. Min Act: -0.0000

Data Index: 543433 (The Pile)

Max Activating Token Index: 856

Text #11

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.5108. Min Act: -0.0000

Data Index: 1327304 (The Pile)

Max Activating Token Index: 760

Text #12

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.4949. Min Act: -0.0000

Data Index: 180858 (The Pile)

Max Activating Token Index: 115

Text #13

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.4790. Min Act: -0.0000

Data Index: 213864 (The Pile)

Max Activating Token Index: 140

Text #14

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.4766. Min Act: -0.0000

Data Index: 1229622 (The Pile)

Max Activating Token Index: 376

Text #15

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.4710. Min Act: -0.0000

Data Index: 1680391 (The Pile)

Max Activating Token Index: 724

Text #16

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.4677. Min Act: -0.0000

Data Index: 315659 (The Pile)

Max Activating Token Index: 235

Text #17

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.4807. Min Act: -0.0000

Data Index: 1427520 (The Pile)

Max Activating Token Index: 873

Text #18

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.4353. Min Act: -0.0000

Data Index: 1554889 (The Pile)

Max Activating Token Index: 123

Text #19

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.4555. Min Act: -0.0000

Data Index: 1174589 (The Pile)

Max Activating Token Index: 46