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

Dataset: The Pile

Neuron 3156 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: 0.4041. Min Range: -0.4041

Max Act: 0.4041. Min Act: -0.0000

Data Index: 74057 (The Pile)

Max Activating Token Index: 984

Text #1

Max Range: 0.4041. Min Range: -0.4041

Max Act: 0.3862. Min Act: -0.0000

Data Index: 1808298 (The Pile)

Max Activating Token Index: 385

Text #2

Max Range: 0.4041. Min Range: -0.4041

Max Act: 0.2761. Min Act: -0.0000

Data Index: 140068 (The Pile)

Max Activating Token Index: 720

Text #3

Max Range: 0.4041. Min Range: -0.4041

Max Act: 0.2028. Min Act: -0.0000

Data Index: 363850 (The Pile)

Max Activating Token Index: 852

Text #4

Max Range: 0.4041. Min Range: -0.4041

Max Act: 0.2591. Min Act: -0.0000

Data Index: 334097 (The Pile)

Max Activating Token Index: 830

Text #5

Max Range: 0.4041. Min Range: -0.4041

Max Act: 0.2560. Min Act: -0.0000

Data Index: 1477236 (The Pile)

Max Activating Token Index: 941

Text #6

Max Range: 0.4041. Min Range: -0.4041

Max Act: 0.2568. Min Act: -0.0000

Data Index: 1420060 (The Pile)

Max Activating Token Index: 978

Text #7

Max Range: 0.4041. Min Range: -0.4041

Max Act: 0.2644. Min Act: -0.0000

Data Index: 892498 (The Pile)

Max Activating Token Index: 854

Text #8

Max Range: 0.4041. Min Range: -0.4041

Max Act: 0.2468. Min Act: -0.0000

Data Index: 65225 (The Pile)

Max Activating Token Index: 858

Text #9

Max Range: 0.4041. Min Range: -0.4041

Max Act: 0.2383. Min Act: -0.0000

Data Index: 473930 (The Pile)

Max Activating Token Index: 189

Text #10

Max Range: 0.4041. Min Range: -0.4041

Max Act: 0.2153. Min Act: -0.0000

Data Index: 950902 (The Pile)

Max Activating Token Index: 606

Text #11

Max Range: 0.4041. Min Range: -0.4041

Max Act: 0.2220. Min Act: -0.0000

Data Index: 220723 (The Pile)

Max Activating Token Index: 846

Text #12

Max Range: 0.4041. Min Range: -0.4041

Max Act: 0.2316. Min Act: -0.0000

Data Index: 454008 (The Pile)

Max Activating Token Index: 987

Text #13

Max Range: 0.4041. Min Range: -0.4041

Max Act: 0.2066. Min Act: -0.0000

Data Index: 182185 (The Pile)

Max Activating Token Index: 1019

Text #14

Max Range: 0.4041. Min Range: -0.4041

Max Act: 0.2089. Min Act: -0.0000

Data Index: 1425460 (The Pile)

Max Activating Token Index: 600

Text #15

Max Range: 0.4041. Min Range: -0.4041

Max Act: 0.2076. Min Act: -0.0000

Data Index: 92974 (The Pile)

Max Activating Token Index: 614

Text #16

Max Range: 0.4041. Min Range: -0.4041

Max Act: 0.1941. Min Act: -0.0000

Data Index: 745423 (The Pile)

Max Activating Token Index: 831

Text #17

Max Range: 0.4041. Min Range: -0.4041

Max Act: 0.2180. Min Act: -0.0000

Data Index: 207489 (The Pile)

Max Activating Token Index: 330

Text #18

Max Range: 0.4041. Min Range: -0.4041

Max Act: 0.2013. Min Act: -0.0000

Data Index: 966859 (The Pile)

Max Activating Token Index: 980

Text #19

Max Range: 0.4041. Min Range: -0.4041

Max Act: 0.2057. Min Act: -0.0000

Data Index: 593263 (The Pile)

Max Activating Token Index: 668