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

Dataset: The Pile

Neuron 4335 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.6601. Min Act: -0.0000

Data Index: 1604487 (The Pile)

Max Activating Token Index: 173

Text #1

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.5183. Min Act: -0.0000

Data Index: 35687 (The Pile)

Max Activating Token Index: 44

Text #2

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.5078. Min Act: -0.0000

Data Index: 843823 (The Pile)

Max Activating Token Index: 635

Text #3

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.4748. Min Act: -0.0000

Data Index: 214698 (The Pile)

Max Activating Token Index: 18

Text #4

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.5040. Min Act: -0.0000

Data Index: 366377 (The Pile)

Max Activating Token Index: 99

Text #5

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.4886. Min Act: -0.0000

Data Index: 59502 (The Pile)

Max Activating Token Index: 613

Text #6

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.4715. Min Act: -0.0000

Data Index: 1680421 (The Pile)

Max Activating Token Index: 56

Text #7

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.4679. Min Act: -0.0000

Data Index: 927329 (The Pile)

Max Activating Token Index: 364

Text #8

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.4492. Min Act: -0.0000

Data Index: 1530426 (The Pile)

Max Activating Token Index: 183

Text #9

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.4716. Min Act: -0.0000

Data Index: 267836 (The Pile)

Max Activating Token Index: 987

Text #10

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.4321. Min Act: -0.0000

Data Index: 671375 (The Pile)

Max Activating Token Index: 562

Text #11

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.4378. Min Act: -0.0000

Data Index: 455273 (The Pile)

Max Activating Token Index: 105

Text #12

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.4310. Min Act: -0.0000

Data Index: 71338 (The Pile)

Max Activating Token Index: 815

Text #13

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.4426. Min Act: -0.0000

Data Index: 611151 (The Pile)

Max Activating Token Index: 138

Text #14

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.4429. Min Act: -0.0000

Data Index: 1730913 (The Pile)

Max Activating Token Index: 384

Text #15

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.3881. Min Act: -0.0000

Data Index: 1938771 (The Pile)

Max Activating Token Index: 835

Text #16

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.4405. Min Act: -0.0000

Data Index: 179817 (The Pile)

Max Activating Token Index: 663

Text #17

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.4401. Min Act: -0.0000

Data Index: 1118675 (The Pile)

Max Activating Token Index: 278

Text #18

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.4236. Min Act: -0.0000

Data Index: 1845795 (The Pile)

Max Activating Token Index: 499

Text #19

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.4328. Min Act: -0.0000

Data Index: 1880857 (The Pile)

Max Activating Token Index: 675