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

Dataset: The Pile

Neuron 2242 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2187. Min Range: -1.2187

Max Act: 1.1911. Min Act: -0.0000

Data Index: 112082 (The Pile)

Max Activating Token Index: 928

Text #1

Max Range: 1.2187. Min Range: -1.2187

Max Act: 1.2187. Min Act: -0.0000

Data Index: 525891 (The Pile)

Max Activating Token Index: 1007

Text #2

Max Range: 1.2187. Min Range: -1.2187

Max Act: 1.0832. Min Act: -0.0000

Data Index: 1971088 (The Pile)

Max Activating Token Index: 331

Text #3

Max Range: 1.2187. Min Range: -1.2187

Max Act: 1.1189. Min Act: -0.0000

Data Index: 714166 (The Pile)

Max Activating Token Index: 754

Text #4

Max Range: 1.2187. Min Range: -1.2187

Max Act: 1.0856. Min Act: -0.0000

Data Index: 1438449 (The Pile)

Max Activating Token Index: 550

Text #5

Max Range: 1.2187. Min Range: -1.2187

Max Act: 1.0881. Min Act: -0.0000

Data Index: 149179 (The Pile)

Max Activating Token Index: 485

Text #6

Max Range: 1.2187. Min Range: -1.2187

Max Act: 1.0199. Min Act: -0.0000

Data Index: 454157 (The Pile)

Max Activating Token Index: 487

Text #7

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.9551. Min Act: -0.0000

Data Index: 992371 (The Pile)

Max Activating Token Index: 1011

Text #8

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.9975. Min Act: -0.0000

Data Index: 1982909 (The Pile)

Max Activating Token Index: 874

Text #9

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.8944. Min Act: -0.0000

Data Index: 594684 (The Pile)

Max Activating Token Index: 893

Text #10

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.8347. Min Act: 0.0000

Data Index: 1555102 (The Pile)

Max Activating Token Index: 1021

Text #11

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.9829. Min Act: -0.0000

Data Index: 1135980 (The Pile)

Max Activating Token Index: 896

Text #12

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.9187. Min Act: -0.0000

Data Index: 1421711 (The Pile)

Max Activating Token Index: 105

Text #13

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.8733. Min Act: -0.0000

Data Index: 1231528 (The Pile)

Max Activating Token Index: 890

Text #14

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.9169. Min Act: -0.0000

Data Index: 1925993 (The Pile)

Max Activating Token Index: 718

Text #15

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.9240. Min Act: -0.0000

Data Index: 1704913 (The Pile)

Max Activating Token Index: 984

Text #16

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.9145. Min Act: -0.0000

Data Index: 745212 (The Pile)

Max Activating Token Index: 958

Text #17

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.9073. Min Act: -0.0000

Data Index: 335314 (The Pile)

Max Activating Token Index: 693

Text #18

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.9228. Min Act: -0.0000

Data Index: 130941 (The Pile)

Max Activating Token Index: 678

Text #19

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.8937. Min Act: -0.0000

Data Index: 293036 (The Pile)

Max Activating Token Index: 778