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

Dataset: The Pile

Neuron 2925 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: 0.5612. Min Range: -0.5612

Max Act: 0.5612. Min Act: -0.0000

Data Index: 1152578 (The Pile)

Max Activating Token Index: 82

Text #1

Max Range: 0.5612. Min Range: -0.5612

Max Act: 0.4210. Min Act: -0.0000

Data Index: 1289056 (The Pile)

Max Activating Token Index: 252

Text #2

Max Range: 0.5612. Min Range: -0.5612

Max Act: 0.3758. Min Act: -0.0000

Data Index: 1123670 (The Pile)

Max Activating Token Index: 639

Text #3

Max Range: 0.5612. Min Range: -0.5612

Max Act: 0.3760. Min Act: -0.0000

Data Index: 1999273 (The Pile)

Max Activating Token Index: 274

Text #4

Max Range: 0.5612. Min Range: -0.5612

Max Act: 0.3877. Min Act: -0.0000

Data Index: 413335 (The Pile)

Max Activating Token Index: 270

Text #5

Max Range: 0.5612. Min Range: -0.5612

Max Act: 0.3809. Min Act: 0.0000

Data Index: 1631529 (The Pile)

Max Activating Token Index: 210

Text #6

Max Range: 0.5612. Min Range: -0.5612

Max Act: 0.3555. Min Act: -0.0000

Data Index: 275822 (The Pile)

Max Activating Token Index: 128

Text #7

Max Range: 0.5612. Min Range: -0.5612

Max Act: 0.3217. Min Act: -0.0000

Data Index: 1995691 (The Pile)

Max Activating Token Index: 643

Text #8

Max Range: 0.5612. Min Range: -0.5612

Max Act: 0.3567. Min Act: -0.0000

Data Index: 486036 (The Pile)

Max Activating Token Index: 292

Text #9

Max Range: 0.5612. Min Range: -0.5612

Max Act: 0.3306. Min Act: -0.0000

Data Index: 1871692 (The Pile)

Max Activating Token Index: 995

Text #10

Max Range: 0.5612. Min Range: -0.5612

Max Act: 0.3624. Min Act: -0.0000

Data Index: 1175969 (The Pile)

Max Activating Token Index: 365

Text #11

Max Range: 0.5612. Min Range: -0.5612

Max Act: 0.3356. Min Act: -0.0000

Data Index: 1949570 (The Pile)

Max Activating Token Index: 603

Text #12

Max Range: 0.5612. Min Range: -0.5612

Max Act: 0.3223. Min Act: -0.0000

Data Index: 639487 (The Pile)

Max Activating Token Index: 540

Text #13

Max Range: 0.5612. Min Range: -0.5612

Max Act: 0.3260. Min Act: -0.0000

Data Index: 324848 (The Pile)

Max Activating Token Index: 660

Text #14

Max Range: 0.5612. Min Range: -0.5612

Max Act: 0.3138. Min Act: -0.0000

Data Index: 1787560 (The Pile)

Max Activating Token Index: 635

Text #15

Max Range: 0.5612. Min Range: -0.5612

Max Act: 0.3216. Min Act: -0.0000

Data Index: 1210317 (The Pile)

Max Activating Token Index: 306

Text #16

Max Range: 0.5612. Min Range: -0.5612

Max Act: 0.3318. Min Act: -0.0000

Data Index: 180280 (The Pile)

Max Activating Token Index: 856

Text #17

Max Range: 0.5612. Min Range: -0.5612

Max Act: 0.3209. Min Act: -0.0000

Data Index: 1710194 (The Pile)

Max Activating Token Index: 927

Text #18

Max Range: 0.5612. Min Range: -0.5612

Max Act: 0.2996. Min Act: -0.0000

Data Index: 30421 (The Pile)

Max Activating Token Index: 828

Text #19

Max Range: 0.5612. Min Range: -0.5612

Max Act: 0.3059. Min Act: -0.0000

Data Index: 728873 (The Pile)

Max Activating Token Index: 268