Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3684 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.2286. Min Range: -1.2286

Max Act: 1.1770. Min Act: -0.0000

Data Index: 844543 (The Pile)

Max Activating Token Index: 840

Text #1

Max Range: 1.2286. Min Range: -1.2286

Max Act: 1.2286. Min Act: -0.0000

Data Index: 1324528 (The Pile)

Max Activating Token Index: 521

Text #2

Max Range: 1.2286. Min Range: -1.2286

Max Act: 1.1565. Min Act: -0.0000

Data Index: 1646632 (The Pile)

Max Activating Token Index: 246

Text #3

Max Range: 1.2286. Min Range: -1.2286

Max Act: 1.1253. Min Act: -0.0000

Data Index: 1009477 (The Pile)

Max Activating Token Index: 173

Text #4

Max Range: 1.2286. Min Range: -1.2286

Max Act: 1.0910. Min Act: -0.0000

Data Index: 1006111 (The Pile)

Max Activating Token Index: 607

Text #5

Max Range: 1.2286. Min Range: -1.2286

Max Act: 1.0566. Min Act: -0.0000

Data Index: 1664064 (The Pile)

Max Activating Token Index: 453

Text #6

Max Range: 1.2286. Min Range: -1.2286

Max Act: 1.0650. Min Act: -0.0000

Data Index: 671950 (The Pile)

Max Activating Token Index: 922

Text #7

Max Range: 1.2286. Min Range: -1.2286

Max Act: 1.0486. Min Act: -0.0000

Data Index: 125695 (The Pile)

Max Activating Token Index: 828

Text #8

Max Range: 1.2286. Min Range: -1.2286

Max Act: 1.0239. Min Act: -0.0000

Data Index: 1605147 (The Pile)

Max Activating Token Index: 888

Text #9

Max Range: 1.2286. Min Range: -1.2286

Max Act: 1.0169. Min Act: -0.0000

Data Index: 528412 (The Pile)

Max Activating Token Index: 760

Text #10

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.9510. Min Act: -0.0000

Data Index: 1302967 (The Pile)

Max Activating Token Index: 877

Text #11

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.9508. Min Act: -0.0000

Data Index: 382658 (The Pile)

Max Activating Token Index: 907

Text #12

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.9702. Min Act: -0.0000

Data Index: 1387191 (The Pile)

Max Activating Token Index: 748

Text #13

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.9757. Min Act: -0.0000

Data Index: 1535521 (The Pile)

Max Activating Token Index: 421

Text #14

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.9339. Min Act: -0.0000

Data Index: 122101 (The Pile)

Max Activating Token Index: 365

Text #15

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.9551. Min Act: -0.0000

Data Index: 718040 (The Pile)

Max Activating Token Index: 879

Text #16

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.9865. Min Act: -0.0000

Data Index: 549746 (The Pile)

Max Activating Token Index: 772

Text #17

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.8707. Min Act: -0.0000

Data Index: 183031 (The Pile)

Max Activating Token Index: 1018

Text #18

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.9571. Min Act: -0.0000

Data Index: 1503996 (The Pile)

Max Activating Token Index: 575

Text #19

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.8995. Min Act: -0.0000

Data Index: 1973889 (The Pile)

Max Activating Token Index: 400