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

Dataset: The Pile

Neuron 2023 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.6228. Min Act: -0.0000

Data Index: 368220 (The Pile)

Max Activating Token Index: 559

Text #1

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.5656. Min Act: -0.0000

Data Index: 452245 (The Pile)

Max Activating Token Index: 938

Text #2

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.5810. Min Act: -0.0000

Data Index: 535628 (The Pile)

Max Activating Token Index: 538

Text #3

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.6037. Min Act: -0.0000

Data Index: 248695 (The Pile)

Max Activating Token Index: 648

Text #4

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.5880. Min Act: -0.0000

Data Index: 391743 (The Pile)

Max Activating Token Index: 201

Text #5

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.5973. Min Act: -0.0000

Data Index: 979371 (The Pile)

Max Activating Token Index: 539

Text #6

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.5684. Min Act: -0.0000

Data Index: 920865 (The Pile)

Max Activating Token Index: 449

Text #7

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.5539. Min Act: -0.0000

Data Index: 1498939 (The Pile)

Max Activating Token Index: 474

Text #8

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.5127. Min Act: -0.0000

Data Index: 1428830 (The Pile)

Max Activating Token Index: 952

Text #9

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.5817. Min Act: -0.0000

Data Index: 1978020 (The Pile)

Max Activating Token Index: 1012

Text #10

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.5856. Min Act: -0.0000

Data Index: 357794 (The Pile)

Max Activating Token Index: 1013

Text #11

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.5269. Min Act: -0.0000

Data Index: 926444 (The Pile)

Max Activating Token Index: 109

Text #12

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.5058. Min Act: -0.0000

Data Index: 825160 (The Pile)

Max Activating Token Index: 717

Text #13

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.5191. Min Act: -0.0000

Data Index: 1697689 (The Pile)

Max Activating Token Index: 900

Text #14

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.5343. Min Act: -0.0000

Data Index: 1294757 (The Pile)

Max Activating Token Index: 618

Text #15

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.5197. Min Act: -0.0000

Data Index: 1030844 (The Pile)

Max Activating Token Index: 366

Text #16

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.5209. Min Act: -0.0000

Data Index: 1218023 (The Pile)

Max Activating Token Index: 488

Text #17

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.5365. Min Act: -0.0000

Data Index: 1715641 (The Pile)

Max Activating Token Index: 338

Text #18

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.5620. Min Act: -0.0000

Data Index: 1205554 (The Pile)

Max Activating Token Index: 700

Text #19

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.5247. Min Act: -0.0000

Data Index: 1479586 (The Pile)

Max Activating Token Index: 21