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

Dataset: The Pile

Neuron 3501 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: 0.8430. Min Range: -0.8430

Max Act: 0.8430. Min Act: -0.0000

Data Index: 151872 (The Pile)

Max Activating Token Index: 479

Text #1

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.7531. Min Act: 0.0000

Data Index: 1100216 (The Pile)

Max Activating Token Index: 641

Text #2

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.7144. Min Act: -0.0000

Data Index: 1511017 (The Pile)

Max Activating Token Index: 606

Text #3

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6247. Min Act: -0.0000

Data Index: 352112 (The Pile)

Max Activating Token Index: 454

Text #4

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6057. Min Act: -0.0000

Data Index: 977067 (The Pile)

Max Activating Token Index: 777

Text #5

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.5887. Min Act: -0.0000

Data Index: 241980 (The Pile)

Max Activating Token Index: 414

Text #6

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.5422. Min Act: -0.0000

Data Index: 277597 (The Pile)

Max Activating Token Index: 909

Text #7

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.5737. Min Act: -0.0000

Data Index: 1072453 (The Pile)

Max Activating Token Index: 975

Text #8

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.5275. Min Act: -0.0000

Data Index: 1721174 (The Pile)

Max Activating Token Index: 649

Text #9

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.5237. Min Act: -0.0000

Data Index: 1741196 (The Pile)

Max Activating Token Index: 997

Text #10

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.5175. Min Act: -0.0000

Data Index: 731677 (The Pile)

Max Activating Token Index: 423

Text #11

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.5138. Min Act: 0.0000

Data Index: 796741 (The Pile)

Max Activating Token Index: 387

Text #12

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.5474. Min Act: -0.0000

Data Index: 1710145 (The Pile)

Max Activating Token Index: 192

Text #13

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.5070. Min Act: -0.0000

Data Index: 806031 (The Pile)

Max Activating Token Index: 484

Text #14

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.5238. Min Act: 0.0000

Data Index: 1326559 (The Pile)

Max Activating Token Index: 679

Text #15

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.5104. Min Act: -0.0000

Data Index: 1524138 (The Pile)

Max Activating Token Index: 947

Text #16

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.4893. Min Act: -0.0000

Data Index: 1312673 (The Pile)

Max Activating Token Index: 895

Text #17

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.4668. Min Act: -0.0000

Data Index: 1453604 (The Pile)

Max Activating Token Index: 635

Text #18

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.5163. Min Act: -0.0000

Data Index: 1059180 (The Pile)

Max Activating Token Index: 806

Text #19

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.5036. Min Act: -0.0000

Data Index: 1457397 (The Pile)

Max Activating Token Index: 348