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

Dataset: The Pile

Neuron 1641 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.6606. Min Act: -0.0000

Data Index: 1975089 (The Pile)

Max Activating Token Index: 137

Text #1

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.6682. Min Act: -0.0000

Data Index: 1936198 (The Pile)

Max Activating Token Index: 932

Text #2

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.5789. Min Act: -0.0000

Data Index: 466111 (The Pile)

Max Activating Token Index: 15

Text #3

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.5241. Min Act: -0.0000

Data Index: 690415 (The Pile)

Max Activating Token Index: 759

Text #4

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.5228. Min Act: -0.0000

Data Index: 1843162 (The Pile)

Max Activating Token Index: 772

Text #5

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.5303. Min Act: -0.0000

Data Index: 775996 (The Pile)

Max Activating Token Index: 71

Text #6

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.5063. Min Act: -0.0000

Data Index: 39703 (The Pile)

Max Activating Token Index: 622

Text #7

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.5066. Min Act: -0.0000

Data Index: 193496 (The Pile)

Max Activating Token Index: 501

Text #8

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.5079. Min Act: -0.0000

Data Index: 700752 (The Pile)

Max Activating Token Index: 198

Text #9

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.5069. Min Act: -0.0000

Data Index: 129138 (The Pile)

Max Activating Token Index: 55

Text #10

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.4248. Min Act: -0.0000

Data Index: 1629993 (The Pile)

Max Activating Token Index: 28

Text #11

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.5093. Min Act: -0.0000

Data Index: 874097 (The Pile)

Max Activating Token Index: 216

Text #12

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.5255. Min Act: -0.0000

Data Index: 858479 (The Pile)

Max Activating Token Index: 800

Text #13

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.5030. Min Act: -0.0000

Data Index: 1459135 (The Pile)

Max Activating Token Index: 705

Text #14

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.4626. Min Act: -0.0000

Data Index: 1059403 (The Pile)

Max Activating Token Index: 1012

Text #15

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.5330. Min Act: -0.0000

Data Index: 860775 (The Pile)

Max Activating Token Index: 198

Text #16

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.5123. Min Act: -0.0000

Data Index: 1158005 (The Pile)

Max Activating Token Index: 67

Text #17

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.5015. Min Act: -0.0000

Data Index: 110390 (The Pile)

Max Activating Token Index: 194

Text #18

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.4823. Min Act: -0.0000

Data Index: 1133332 (The Pile)

Max Activating Token Index: 691

Text #19

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.4820. Min Act: -0.0000

Data Index: 1596798 (The Pile)

Max Activating Token Index: 360