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

Dataset: The Pile

Neuron 4927 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: 0.3978. Min Range: -0.3978

Max Act: 0.3978. Min Act: -0.0000

Data Index: 926980 (The Pile)

Max Activating Token Index: 387

Text #1

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3745. Min Act: -0.0000

Data Index: 1137374 (The Pile)

Max Activating Token Index: 713

Text #2

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3097. Min Act: -0.0000

Data Index: 358442 (The Pile)

Max Activating Token Index: 965

Text #3

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3392. Min Act: -0.0000

Data Index: 688197 (The Pile)

Max Activating Token Index: 648

Text #4

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3290. Min Act: -0.0000

Data Index: 1543392 (The Pile)

Max Activating Token Index: 241

Text #5

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3464. Min Act: -0.0000

Data Index: 428933 (The Pile)

Max Activating Token Index: 925

Text #6

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3120. Min Act: -0.0000

Data Index: 1747273 (The Pile)

Max Activating Token Index: 564

Text #7

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3091. Min Act: -0.0000

Data Index: 1973542 (The Pile)

Max Activating Token Index: 554

Text #8

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3058. Min Act: -0.0000

Data Index: 444295 (The Pile)

Max Activating Token Index: 44

Text #9

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.2935. Min Act: -0.0000

Data Index: 170416 (The Pile)

Max Activating Token Index: 697

Text #10

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3209. Min Act: -0.0000

Data Index: 1887803 (The Pile)

Max Activating Token Index: 696

Text #11

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3037. Min Act: -0.0000

Data Index: 589036 (The Pile)

Max Activating Token Index: 472

Text #12

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.2881. Min Act: -0.0000

Data Index: 1085338 (The Pile)

Max Activating Token Index: 796

Text #13

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.2965. Min Act: -0.0000

Data Index: 1902459 (The Pile)

Max Activating Token Index: 386

Text #14

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.2820. Min Act: -0.0000

Data Index: 935786 (The Pile)

Max Activating Token Index: 70

Text #15

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.2902. Min Act: -0.0000

Data Index: 379054 (The Pile)

Max Activating Token Index: 461

Text #16

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3001. Min Act: -0.0000

Data Index: 668079 (The Pile)

Max Activating Token Index: 328

Text #17

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.2756. Min Act: -0.0000

Data Index: 1100649 (The Pile)

Max Activating Token Index: 665

Text #18

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.2901. Min Act: -0.0000

Data Index: 1712628 (The Pile)

Max Activating Token Index: 277

Text #19

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.2690. Min Act: -0.0000

Data Index: 1999330 (The Pile)

Max Activating Token Index: 342