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

Dataset: The Pile

Neuron 4344 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7369. Min Range: -3.7369

Max Act: 3.6881. Min Act: -0.0000

Data Index: 604377 (The Pile)

Max Activating Token Index: 392

Text #1

Max Range: 3.7369. Min Range: -3.7369

Max Act: 3.6292. Min Act: -0.0000

Data Index: 937240 (The Pile)

Max Activating Token Index: 556

Text #2

Max Range: 3.7369. Min Range: -3.7369

Max Act: 3.7369. Min Act: -0.0000

Data Index: 332092 (The Pile)

Max Activating Token Index: 925

Text #3

Max Range: 3.7369. Min Range: -3.7369

Max Act: 3.4824. Min Act: -0.0000

Data Index: 835243 (The Pile)

Max Activating Token Index: 524

Text #4

Max Range: 3.7369. Min Range: -3.7369

Max Act: 3.3924. Min Act: -0.0000

Data Index: 840057 (The Pile)

Max Activating Token Index: 716

Text #5

Max Range: 3.7369. Min Range: -3.7369

Max Act: 3.3531. Min Act: -0.0000

Data Index: 1914662 (The Pile)

Max Activating Token Index: 662

Text #6

Max Range: 3.7369. Min Range: -3.7369

Max Act: 3.3019. Min Act: -0.0000

Data Index: 582221 (The Pile)

Max Activating Token Index: 987

Text #7

Max Range: 3.7369. Min Range: -3.7369

Max Act: 3.2812. Min Act: -0.0000

Data Index: 1160159 (The Pile)

Max Activating Token Index: 528

Text #8

Max Range: 3.7369. Min Range: -3.7369

Max Act: 3.2736. Min Act: -0.0000

Data Index: 40192 (The Pile)

Max Activating Token Index: 642

Text #9

Max Range: 3.7369. Min Range: -3.7369

Max Act: 3.4218. Min Act: -0.0000

Data Index: 622093 (The Pile)

Max Activating Token Index: 593

Text #10

Max Range: 3.7369. Min Range: -3.7369

Max Act: 3.1299. Min Act: -0.0000

Data Index: 932356 (The Pile)

Max Activating Token Index: 14

Text #11

Max Range: 3.7369. Min Range: -3.7369

Max Act: 3.1083. Min Act: -0.0000

Data Index: 430952 (The Pile)

Max Activating Token Index: 797

Text #12

Max Range: 3.7369. Min Range: -3.7369

Max Act: 3.3287. Min Act: -0.0000

Data Index: 1831651 (The Pile)

Max Activating Token Index: 672

Text #13

Max Range: 3.7369. Min Range: -3.7369

Max Act: 3.0040. Min Act: -0.0000

Data Index: 307216 (The Pile)

Max Activating Token Index: 569

Text #14

Max Range: 3.7369. Min Range: -3.7369

Max Act: 3.1453. Min Act: -0.0000

Data Index: 485801 (The Pile)

Max Activating Token Index: 831

Text #15

Max Range: 3.7369. Min Range: -3.7369

Max Act: 3.2732. Min Act: -0.0000

Data Index: 185079 (The Pile)

Max Activating Token Index: 917

Text #16

Max Range: 3.7369. Min Range: -3.7369

Max Act: 3.1389. Min Act: -0.0000

Data Index: 1606874 (The Pile)

Max Activating Token Index: 691

Text #17

Max Range: 3.7369. Min Range: -3.7369

Max Act: 3.0018. Min Act: -0.0000

Data Index: 1775451 (The Pile)

Max Activating Token Index: 321

Text #18

Max Range: 3.7369. Min Range: -3.7369

Max Act: 3.0969. Min Act: -0.0000

Data Index: 1495402 (The Pile)

Max Activating Token Index: 245

Text #19

Max Range: 3.7369. Min Range: -3.7369

Max Act: 3.1060. Min Act: -0.0000

Data Index: 211537 (The Pile)

Max Activating Token Index: 1009