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

Dataset: The Pile

Neuron 1324 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7057. Min Range: -0.7057

Max Act: 0.7057. Min Act: -0.0000

Data Index: 427027 (The Pile)

Max Activating Token Index: 415

Text #1

Max Range: 0.7057. Min Range: -0.7057

Max Act: 0.6176. Min Act: -0.0000

Data Index: 145639 (The Pile)

Max Activating Token Index: 1005

Text #2

Max Range: 0.7057. Min Range: -0.7057

Max Act: 0.6243. Min Act: -0.0000

Data Index: 1219639 (The Pile)

Max Activating Token Index: 839

Text #3

Max Range: 0.7057. Min Range: -0.7057

Max Act: 0.6507. Min Act: -0.0000

Data Index: 447620 (The Pile)

Max Activating Token Index: 597

Text #4

Max Range: 0.7057. Min Range: -0.7057

Max Act: 0.5659. Min Act: -0.0000

Data Index: 1341026 (The Pile)

Max Activating Token Index: 700

Text #5

Max Range: 0.7057. Min Range: -0.7057

Max Act: 0.4874. Min Act: -0.0001

Data Index: 1978695 (The Pile)

Max Activating Token Index: 65

Text #6

Max Range: 0.7057. Min Range: -0.7057

Max Act: 0.5010. Min Act: -0.0000

Data Index: 1319540 (The Pile)

Max Activating Token Index: 213

Text #7

Max Range: 0.7057. Min Range: -0.7057

Max Act: 0.4941. Min Act: -0.0000

Data Index: 1537066 (The Pile)

Max Activating Token Index: 290

Text #8

Max Range: 0.7057. Min Range: -0.7057

Max Act: 0.4658. Min Act: -0.0000

Data Index: 1582824 (The Pile)

Max Activating Token Index: 601

Text #9

Max Range: 0.7057. Min Range: -0.7057

Max Act: 0.4844. Min Act: -0.0000

Data Index: 938058 (The Pile)

Max Activating Token Index: 492

Text #10

Max Range: 0.7057. Min Range: -0.7057

Max Act: 0.4658. Min Act: -0.0000

Data Index: 1571538 (The Pile)

Max Activating Token Index: 968

Text #11

Max Range: 0.7057. Min Range: -0.7057

Max Act: 0.5233. Min Act: -0.0000

Data Index: 1076329 (The Pile)

Max Activating Token Index: 49

Text #12

Max Range: 0.7057. Min Range: -0.7057

Max Act: 0.4623. Min Act: -0.0000

Data Index: 535415 (The Pile)

Max Activating Token Index: 18

Text #13

Max Range: 0.7057. Min Range: -0.7057

Max Act: 0.4623. Min Act: -0.0000

Data Index: 57074 (The Pile)

Max Activating Token Index: 888

Text #14

Max Range: 0.7057. Min Range: -0.7057

Max Act: 0.4728. Min Act: -0.0000

Data Index: 1170017 (The Pile)

Max Activating Token Index: 214

Text #15

Max Range: 0.7057. Min Range: -0.7057

Max Act: 0.4252. Min Act: -0.0000

Data Index: 1213467 (The Pile)

Max Activating Token Index: 553

Text #16

Max Range: 0.7057. Min Range: -0.7057

Max Act: 0.4375. Min Act: -0.0000

Data Index: 15095 (The Pile)

Max Activating Token Index: 697

Text #17

Max Range: 0.7057. Min Range: -0.7057

Max Act: 0.4444. Min Act: -0.0000

Data Index: 857063 (The Pile)

Max Activating Token Index: 511

Text #18

Max Range: 0.7057. Min Range: -0.7057

Max Act: 0.4836. Min Act: -0.0000

Data Index: 910607 (The Pile)

Max Activating Token Index: 445

Text #19

Max Range: 0.7057. Min Range: -0.7057

Max Act: 0.4752. Min Act: -0.0000

Data Index: 832235 (The Pile)

Max Activating Token Index: 547