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

Dataset: The Pile

Neuron 894 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.6340. Min Act: -0.0000

Data Index: 466059 (The Pile)

Max Activating Token Index: 500

Text #1

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.5902. Min Act: -0.0000

Data Index: 1633712 (The Pile)

Max Activating Token Index: 88

Text #2

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.5699. Min Act: -0.0000

Data Index: 1715774 (The Pile)

Max Activating Token Index: 345

Text #3

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.5898. Min Act: -0.0000

Data Index: 191300 (The Pile)

Max Activating Token Index: 675

Text #4

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.5457. Min Act: 0.0000

Data Index: 458366 (The Pile)

Max Activating Token Index: 905

Text #5

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.5805. Min Act: -0.0000

Data Index: 887600 (The Pile)

Max Activating Token Index: 915

Text #6

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.4820. Min Act: -0.0000

Data Index: 940688 (The Pile)

Max Activating Token Index: 296

Text #7

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.4944. Min Act: -0.0000

Data Index: 768350 (The Pile)

Max Activating Token Index: 118

Text #8

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.4417. Min Act: -0.0000

Data Index: 676116 (The Pile)

Max Activating Token Index: 817

Text #9

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.4666. Min Act: -0.0000

Data Index: 1294824 (The Pile)

Max Activating Token Index: 606

Text #10

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.4735. Min Act: -0.0000

Data Index: 214605 (The Pile)

Max Activating Token Index: 691

Text #11

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.4760. Min Act: -0.0000

Data Index: 1270567 (The Pile)

Max Activating Token Index: 249

Text #12

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.4631. Min Act: -0.0000

Data Index: 1136737 (The Pile)

Max Activating Token Index: 1019

Text #13

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.4638. Min Act: 0.0000

Data Index: 397930 (The Pile)

Max Activating Token Index: 60

Text #14

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.4404. Min Act: -0.0000

Data Index: 809390 (The Pile)

Max Activating Token Index: 1013

Text #15

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.4642. Min Act: 0.0000

Data Index: 1442066 (The Pile)

Max Activating Token Index: 397

Text #16

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.4875. Min Act: -0.0000

Data Index: 1820660 (The Pile)

Max Activating Token Index: 199

Text #17

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.4272. Min Act: -0.0000

Data Index: 763494 (The Pile)

Max Activating Token Index: 355

Text #18

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.4028. Min Act: -0.0000

Data Index: 1622823 (The Pile)

Max Activating Token Index: 922

Text #19

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.4765. Min Act: -0.0000

Data Index: 1151515 (The Pile)

Max Activating Token Index: 682