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

Dataset: The Pile

Neuron 4663 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: 3.2948. Min Range: -3.2948

Max Act: 3.2948. Min Act: -0.0000

Data Index: 1621718 (The Pile)

Max Activating Token Index: 890

Text #1

Max Range: 3.2948. Min Range: -3.2948

Max Act: 3.2049. Min Act: -0.0000

Data Index: 1763854 (The Pile)

Max Activating Token Index: 814

Text #2

Max Range: 3.2948. Min Range: -3.2948

Max Act: 3.1008. Min Act: -0.0000

Data Index: 963561 (The Pile)

Max Activating Token Index: 441

Text #3

Max Range: 3.2948. Min Range: -3.2948

Max Act: 3.2141. Min Act: -0.0000

Data Index: 1734819 (The Pile)

Max Activating Token Index: 443

Text #4

Max Range: 3.2948. Min Range: -3.2948

Max Act: 3.2152. Min Act: -0.0000

Data Index: 1285411 (The Pile)

Max Activating Token Index: 1004

Text #5

Max Range: 3.2948. Min Range: -3.2948

Max Act: 3.0851. Min Act: -0.0000

Data Index: 1401147 (The Pile)

Max Activating Token Index: 626

Text #6

Max Range: 3.2948. Min Range: -3.2948

Max Act: 3.1687. Min Act: -0.0000

Data Index: 1467363 (The Pile)

Max Activating Token Index: 52

Text #7

Max Range: 3.2948. Min Range: -3.2948

Max Act: 3.0000. Min Act: -0.0000

Data Index: 431205 (The Pile)

Max Activating Token Index: 299

Text #8

Max Range: 3.2948. Min Range: -3.2948

Max Act: 2.8588. Min Act: -0.0000

Data Index: 1177699 (The Pile)

Max Activating Token Index: 201

Text #9

Max Range: 3.2948. Min Range: -3.2948

Max Act: 3.1199. Min Act: -0.0000

Data Index: 278788 (The Pile)

Max Activating Token Index: 44

Text #10

Max Range: 3.2948. Min Range: -3.2948

Max Act: 3.1097. Min Act: -0.0001

Data Index: 1966249 (The Pile)

Max Activating Token Index: 423

Text #11

Max Range: 3.2948. Min Range: -3.2948

Max Act: 2.9483. Min Act: -0.0000

Data Index: 1726846 (The Pile)

Max Activating Token Index: 415

Text #12

Max Range: 3.2948. Min Range: -3.2948

Max Act: 2.9806. Min Act: -0.0000

Data Index: 1081082 (The Pile)

Max Activating Token Index: 930

Text #13

Max Range: 3.2948. Min Range: -3.2948

Max Act: 3.0857. Min Act: -0.0000

Data Index: 797367 (The Pile)

Max Activating Token Index: 686

Text #14

Max Range: 3.2948. Min Range: -3.2948

Max Act: 2.9340. Min Act: -0.0000

Data Index: 614119 (The Pile)

Max Activating Token Index: 765

Text #15

Max Range: 3.2948. Min Range: -3.2948

Max Act: 2.9120. Min Act: -0.0000

Data Index: 1649600 (The Pile)

Max Activating Token Index: 802

Text #16

Max Range: 3.2948. Min Range: -3.2948

Max Act: 3.1810. Min Act: -0.0000

Data Index: 628308 (The Pile)

Max Activating Token Index: 1006

Text #17

Max Range: 3.2948. Min Range: -3.2948

Max Act: 3.1825. Min Act: -0.0000

Data Index: 931764 (The Pile)

Max Activating Token Index: 1014

Text #18

Max Range: 3.2948. Min Range: -3.2948

Max Act: 3.1758. Min Act: -0.0000

Data Index: 583100 (The Pile)

Max Activating Token Index: 718

Text #19

Max Range: 3.2948. Min Range: -3.2948

Max Act: 2.7606. Min Act: -0.0000

Data Index: 438187 (The Pile)

Max Activating Token Index: 903