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

Dataset: The Pile

Neuron 3170 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: 1.1930. Min Range: -1.1930

Max Act: 1.1882. Min Act: -0.0000

Data Index: 269969 (The Pile)

Max Activating Token Index: 522

Text #1

Max Range: 1.1930. Min Range: -1.1930

Max Act: 1.1930. Min Act: -0.0000

Data Index: 1664480 (The Pile)

Max Activating Token Index: 451

Text #2

Max Range: 1.1930. Min Range: -1.1930

Max Act: 1.1834. Min Act: -0.0000

Data Index: 199259 (The Pile)

Max Activating Token Index: 646

Text #3

Max Range: 1.1930. Min Range: -1.1930

Max Act: 1.1684. Min Act: -0.0000

Data Index: 526969 (The Pile)

Max Activating Token Index: 409

Text #4

Max Range: 1.1930. Min Range: -1.1930

Max Act: 1.0809. Min Act: -0.0000

Data Index: 1674440 (The Pile)

Max Activating Token Index: 236

Text #5

Max Range: 1.1930. Min Range: -1.1930

Max Act: 1.1197. Min Act: -0.0000

Data Index: 595308 (The Pile)

Max Activating Token Index: 436

Text #6

Max Range: 1.1930. Min Range: -1.1930

Max Act: 1.1123. Min Act: -0.0000

Data Index: 483752 (The Pile)

Max Activating Token Index: 390

Text #7

Max Range: 1.1930. Min Range: -1.1930

Max Act: 1.0891. Min Act: -0.0000

Data Index: 1223361 (The Pile)

Max Activating Token Index: 222

Text #8

Max Range: 1.1930. Min Range: -1.1930

Max Act: 1.0702. Min Act: -0.0000

Data Index: 1120254 (The Pile)

Max Activating Token Index: 469

Text #9

Max Range: 1.1930. Min Range: -1.1930

Max Act: 1.0569. Min Act: -0.0000

Data Index: 132303 (The Pile)

Max Activating Token Index: 344

Text #10

Max Range: 1.1930. Min Range: -1.1930

Max Act: 1.0744. Min Act: -0.0000

Data Index: 1897895 (The Pile)

Max Activating Token Index: 241

Text #11

Max Range: 1.1930. Min Range: -1.1930

Max Act: 1.0422. Min Act: -0.0000

Data Index: 1968780 (The Pile)

Max Activating Token Index: 296

Text #12

Max Range: 1.1930. Min Range: -1.1930

Max Act: 0.9099. Min Act: -0.0000

Data Index: 1282713 (The Pile)

Max Activating Token Index: 51

Text #13

Max Range: 1.1930. Min Range: -1.1930

Max Act: 1.0292. Min Act: -0.0000

Data Index: 987452 (The Pile)

Max Activating Token Index: 256

Text #14

Max Range: 1.1930. Min Range: -1.1930

Max Act: 1.0892. Min Act: -0.0000

Data Index: 517477 (The Pile)

Max Activating Token Index: 215

Text #15

Max Range: 1.1930. Min Range: -1.1930

Max Act: 0.9694. Min Act: -0.0000

Data Index: 1621955 (The Pile)

Max Activating Token Index: 425

Text #16

Max Range: 1.1930. Min Range: -1.1930

Max Act: 0.9742. Min Act: -0.0000

Data Index: 1231574 (The Pile)

Max Activating Token Index: 793

Text #17

Max Range: 1.1930. Min Range: -1.1930

Max Act: 0.9182. Min Act: -0.0000

Data Index: 1449336 (The Pile)

Max Activating Token Index: 356

Text #18

Max Range: 1.1930. Min Range: -1.1930

Max Act: 0.9561. Min Act: -0.0000

Data Index: 1833446 (The Pile)

Max Activating Token Index: 858

Text #19

Max Range: 1.1930. Min Range: -1.1930

Max Act: 0.9783. Min Act: -0.0000

Data Index: 1643254 (The Pile)

Max Activating Token Index: 332