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

Dataset: The Pile

Neuron 2954 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: 0.7632. Min Range: -0.7632

Max Act: 0.7632. Min Act: -0.0000

Data Index: 1117741 (The Pile)

Max Activating Token Index: 196

Text #1

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.6735. Min Act: -0.0000

Data Index: 1201854 (The Pile)

Max Activating Token Index: 566

Text #2

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.6140. Min Act: -0.0000

Data Index: 699582 (The Pile)

Max Activating Token Index: 778

Text #3

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.6071. Min Act: -0.0000

Data Index: 1684098 (The Pile)

Max Activating Token Index: 391

Text #4

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.5020. Min Act: -0.0000

Data Index: 201590 (The Pile)

Max Activating Token Index: 965

Text #5

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.4965. Min Act: -0.0000

Data Index: 1987249 (The Pile)

Max Activating Token Index: 217

Text #6

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.4835. Min Act: -0.0000

Data Index: 563577 (The Pile)

Max Activating Token Index: 763

Text #7

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.4318. Min Act: 0.0000

Data Index: 1526555 (The Pile)

Max Activating Token Index: 100

Text #8

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.4156. Min Act: -0.0000

Data Index: 1502049 (The Pile)

Max Activating Token Index: 714

Text #9

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.4575. Min Act: -0.0000

Data Index: 1702795 (The Pile)

Max Activating Token Index: 47

Text #10

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.4259. Min Act: -0.0000

Data Index: 958160 (The Pile)

Max Activating Token Index: 115

Text #11

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.4404. Min Act: -0.0000

Data Index: 342133 (The Pile)

Max Activating Token Index: 243

Text #12

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.4049. Min Act: -0.0000

Data Index: 1689556 (The Pile)

Max Activating Token Index: 753

Text #13

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.4100. Min Act: -0.0000

Data Index: 1800999 (The Pile)

Max Activating Token Index: 279

Text #14

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.4208. Min Act: -0.0000

Data Index: 24755 (The Pile)

Max Activating Token Index: 201

Text #15

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.4258. Min Act: -0.0000

Data Index: 1004593 (The Pile)

Max Activating Token Index: 987

Text #16

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.3972. Min Act: -0.0000

Data Index: 1094078 (The Pile)

Max Activating Token Index: 987

Text #17

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.4064. Min Act: -0.0000

Data Index: 1166000 (The Pile)

Max Activating Token Index: 456

Text #18

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.3978. Min Act: 0.0000

Data Index: 386905 (The Pile)

Max Activating Token Index: 121

Text #19

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.4041. Min Act: -0.0000

Data Index: 1163327 (The Pile)

Max Activating Token Index: 193