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

Dataset: The Pile

Neuron 4864 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: 1.1327. Min Range: -1.1327

Max Act: 1.1327. Min Act: -0.0000

Data Index: 1328285 (The Pile)

Max Activating Token Index: 753

Text #1

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.9208. Min Act: -0.0000

Data Index: 413226 (The Pile)

Max Activating Token Index: 996

Text #2

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.9290. Min Act: -0.0000

Data Index: 65242 (The Pile)

Max Activating Token Index: 344

Text #3

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.8043. Min Act: -0.0000

Data Index: 774293 (The Pile)

Max Activating Token Index: 536

Text #4

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.7531. Min Act: -0.0000

Data Index: 568206 (The Pile)

Max Activating Token Index: 441

Text #5

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.7886. Min Act: -0.0000

Data Index: 816082 (The Pile)

Max Activating Token Index: 252

Text #6

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.7362. Min Act: -0.0000

Data Index: 1041542 (The Pile)

Max Activating Token Index: 340

Text #7

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.7200. Min Act: -0.0000

Data Index: 1204292 (The Pile)

Max Activating Token Index: 126

Text #8

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.5809. Min Act: -0.0000

Data Index: 1461455 (The Pile)

Max Activating Token Index: 572

Text #9

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.6003. Min Act: -0.0000

Data Index: 1868823 (The Pile)

Max Activating Token Index: 477

Text #10

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.5699. Min Act: -0.0000

Data Index: 666121 (The Pile)

Max Activating Token Index: 682

Text #11

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.5273. Min Act: -0.0000

Data Index: 962743 (The Pile)

Max Activating Token Index: 769

Text #12

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.5794. Min Act: -0.0000

Data Index: 564149 (The Pile)

Max Activating Token Index: 697

Text #13

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.5951. Min Act: -0.0000

Data Index: 984482 (The Pile)

Max Activating Token Index: 476

Text #14

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.5608. Min Act: -0.0000

Data Index: 291528 (The Pile)

Max Activating Token Index: 709

Text #15

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.5598. Min Act: -0.0000

Data Index: 181872 (The Pile)

Max Activating Token Index: 272

Text #16

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.5910. Min Act: -0.0000

Data Index: 1068074 (The Pile)

Max Activating Token Index: 457

Text #17

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.5763. Min Act: -0.0000

Data Index: 1518042 (The Pile)

Max Activating Token Index: 546

Text #18

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.5854. Min Act: -0.0000

Data Index: 1844537 (The Pile)

Max Activating Token Index: 573

Text #19

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.5636. Min Act: -0.0000

Data Index: 1896642 (The Pile)

Max Activating Token Index: 327