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

Dataset: The Pile

Neuron 5041 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: 1.9343. Min Range: -1.9343

Max Act: 1.9343. Min Act: -0.0000

Data Index: 276340 (The Pile)

Max Activating Token Index: 476

Text #1

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.8590. Min Act: -0.0000

Data Index: 1076932 (The Pile)

Max Activating Token Index: 256

Text #2

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.7469. Min Act: -0.0000

Data Index: 1532370 (The Pile)

Max Activating Token Index: 400

Text #3

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.4921. Min Act: -0.0000

Data Index: 1761349 (The Pile)

Max Activating Token Index: 216

Text #4

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.5853. Min Act: -0.0000

Data Index: 1951433 (The Pile)

Max Activating Token Index: 338

Text #5

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.6469. Min Act: -0.0000

Data Index: 225641 (The Pile)

Max Activating Token Index: 506

Text #6

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.5508. Min Act: -0.0000

Data Index: 1520930 (The Pile)

Max Activating Token Index: 229

Text #7

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.5322. Min Act: -0.0000

Data Index: 1893868 (The Pile)

Max Activating Token Index: 383

Text #8

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.6094. Min Act: -0.0000

Data Index: 478186 (The Pile)

Max Activating Token Index: 182

Text #9

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.4983. Min Act: -0.0000

Data Index: 1971174 (The Pile)

Max Activating Token Index: 390

Text #10

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.4813. Min Act: -0.0000

Data Index: 1234048 (The Pile)

Max Activating Token Index: 66

Text #11

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.3247. Min Act: -0.0000

Data Index: 935951 (The Pile)

Max Activating Token Index: 256

Text #12

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.3859. Min Act: -0.0000

Data Index: 928439 (The Pile)

Max Activating Token Index: 480

Text #13

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.3694. Min Act: -0.0000

Data Index: 350428 (The Pile)

Max Activating Token Index: 593

Text #14

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.3645. Min Act: -0.0000

Data Index: 760146 (The Pile)

Max Activating Token Index: 128

Text #15

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.2666. Min Act: -0.0000

Data Index: 1471866 (The Pile)

Max Activating Token Index: 846

Text #16

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.2766. Min Act: -0.0000

Data Index: 1386690 (The Pile)

Max Activating Token Index: 765

Text #17

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.2764. Min Act: -0.0000

Data Index: 1802658 (The Pile)

Max Activating Token Index: 21

Text #18

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.3528. Min Act: -0.0000

Data Index: 1170887 (The Pile)

Max Activating Token Index: 72

Text #19

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.2599. Min Act: -0.0000

Data Index: 1778251 (The Pile)

Max Activating Token Index: 419