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

Dataset: The Pile

Neuron 2387 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: 1.6974. Min Range: -1.6974

Max Act: 1.6974. Min Act: -0.0000

Data Index: 444664 (The Pile)

Max Activating Token Index: 50

Text #1

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.6110. Min Act: -0.0000

Data Index: 546288 (The Pile)

Max Activating Token Index: 24

Text #2

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.5764. Min Act: -0.0000

Data Index: 1697382 (The Pile)

Max Activating Token Index: 834

Text #3

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.5644. Min Act: -0.0000

Data Index: 1706679 (The Pile)

Max Activating Token Index: 142

Text #4

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.5861. Min Act: -0.0000

Data Index: 1526830 (The Pile)

Max Activating Token Index: 605

Text #5

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.4426. Min Act: -0.0000

Data Index: 79836 (The Pile)

Max Activating Token Index: 107

Text #6

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.4917. Min Act: -0.0000

Data Index: 666082 (The Pile)

Max Activating Token Index: 21

Text #7

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.3025. Min Act: -0.0000

Data Index: 1893819 (The Pile)

Max Activating Token Index: 82

Text #8

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.2252. Min Act: -0.0000

Data Index: 272264 (The Pile)

Max Activating Token Index: 22

Text #9

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.2107. Min Act: -0.0000

Data Index: 1434293 (The Pile)

Max Activating Token Index: 637

Text #10

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.1901. Min Act: -0.0000

Data Index: 648350 (The Pile)

Max Activating Token Index: 117

Text #11

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.0856. Min Act: -0.0000

Data Index: 158059 (The Pile)

Max Activating Token Index: 155

Text #12

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.1510. Min Act: -0.0000

Data Index: 1663485 (The Pile)

Max Activating Token Index: 1010

Text #13

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.1156. Min Act: -0.0000

Data Index: 1796794 (The Pile)

Max Activating Token Index: 926

Text #14

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.1114. Min Act: -0.0000

Data Index: 223011 (The Pile)

Max Activating Token Index: 120

Text #15

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.0610. Min Act: -0.0000

Data Index: 553930 (The Pile)

Max Activating Token Index: 184

Text #16

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.0393. Min Act: -0.0000

Data Index: 1490513 (The Pile)

Max Activating Token Index: 126

Text #17

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.0048. Min Act: -0.0000

Data Index: 1264963 (The Pile)

Max Activating Token Index: 124

Text #18

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.1082. Min Act: -0.0000

Data Index: 625431 (The Pile)

Max Activating Token Index: 834

Text #19

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.0100. Min Act: -0.0000

Data Index: 867282 (The Pile)

Max Activating Token Index: 359