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

Dataset: The Pile

Neuron 919 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1574. Min Act: -0.0000

Data Index: 1979190 (The Pile)

Max Activating Token Index: 441

Text #1

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1115. Min Act: -0.0000

Data Index: 356676 (The Pile)

Max Activating Token Index: 33

Text #2

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1109. Min Act: -0.0000

Data Index: 898391 (The Pile)

Max Activating Token Index: 26

Text #3

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1147. Min Act: -0.0000

Data Index: 1453893 (The Pile)

Max Activating Token Index: 645

Text #4

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1165. Min Act: -0.0000

Data Index: 184411 (The Pile)

Max Activating Token Index: 36

Text #5

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1058. Min Act: -0.0000

Data Index: 1394107 (The Pile)

Max Activating Token Index: 164

Text #6

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1078. Min Act: -0.0000

Data Index: 102269 (The Pile)

Max Activating Token Index: 17

Text #7

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1090. Min Act: -0.0000

Data Index: 1780956 (The Pile)

Max Activating Token Index: 486

Text #8

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.0974. Min Act: -0.0000

Data Index: 1066636 (The Pile)

Max Activating Token Index: 140

Text #9

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1108. Min Act: -0.0000

Data Index: 183371 (The Pile)

Max Activating Token Index: 137

Text #10

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.0948. Min Act: -0.0000

Data Index: 461429 (The Pile)

Max Activating Token Index: 956

Text #11

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1041. Min Act: -0.0000

Data Index: 1015369 (The Pile)

Max Activating Token Index: 414

Text #12

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1105. Min Act: -0.0000

Data Index: 1003301 (The Pile)

Max Activating Token Index: 629

Text #13

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1001. Min Act: -0.0000

Data Index: 356093 (The Pile)

Max Activating Token Index: 73

Text #14

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.0987. Min Act: -0.0000

Data Index: 1905119 (The Pile)

Max Activating Token Index: 8

Text #15

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.0955. Min Act: -0.0000

Data Index: 1136945 (The Pile)

Max Activating Token Index: 402

Text #16

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.0986. Min Act: -0.0000

Data Index: 1651191 (The Pile)

Max Activating Token Index: 14

Text #17

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.0879. Min Act: -0.0000

Data Index: 1788419 (The Pile)

Max Activating Token Index: 724

Text #18

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.0973. Min Act: -0.0000

Data Index: 1680683 (The Pile)

Max Activating Token Index: 67

Text #19

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.0915. Min Act: -0.0000

Data Index: 723419 (The Pile)

Max Activating Token Index: 788