Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 171 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1244. Min Act: -0.0000

Data Index: 1203947 (The Pile)

Max Activating Token Index: 754

Text #1

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1127. Min Act: -0.0000

Data Index: 502886 (The Pile)

Max Activating Token Index: 951

Text #2

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1199. Min Act: -0.0000

Data Index: 977660 (The Pile)

Max Activating Token Index: 972

Text #3

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1147. Min Act: -0.0000

Data Index: 1887161 (The Pile)

Max Activating Token Index: 252

Text #4

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1178. Min Act: -0.0000

Data Index: 1350757 (The Pile)

Max Activating Token Index: 64

Text #5

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1063. Min Act: -0.0000

Data Index: 1500551 (The Pile)

Max Activating Token Index: 561

Text #6

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1104. Min Act: -0.0000

Data Index: 480759 (The Pile)

Max Activating Token Index: 443

Text #7

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1135. Min Act: -0.0000

Data Index: 834714 (The Pile)

Max Activating Token Index: 470

Text #8

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1072. Min Act: -0.0000

Data Index: 116820 (The Pile)

Max Activating Token Index: 223

Text #9

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1052. Min Act: -0.0000

Data Index: 192649 (The Pile)

Max Activating Token Index: 68

Text #10

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1159. Min Act: -0.0000

Data Index: 48369 (The Pile)

Max Activating Token Index: 892

Text #11

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1115. Min Act: -0.0000

Data Index: 1557604 (The Pile)

Max Activating Token Index: 298

Text #12

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1141. Min Act: -0.0000

Data Index: 1797740 (The Pile)

Max Activating Token Index: 825

Text #13

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1059. Min Act: -0.0000

Data Index: 1635086 (The Pile)

Max Activating Token Index: 426

Text #14

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1036. Min Act: -0.0000

Data Index: 80513 (The Pile)

Max Activating Token Index: 604

Text #15

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0957. Min Act: -0.0000

Data Index: 223597 (The Pile)

Max Activating Token Index: 930

Text #16

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1019. Min Act: -0.0000

Data Index: 1816753 (The Pile)

Max Activating Token Index: 528

Text #17

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0982. Min Act: -0.0000

Data Index: 753538 (The Pile)

Max Activating Token Index: 92

Text #18

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0936. Min Act: -0.0000

Data Index: 1366518 (The Pile)

Max Activating Token Index: 825

Text #19

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1039. Min Act: -0.0000

Data Index: 844661 (The Pile)

Max Activating Token Index: 819