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

Dataset: The Pile

Neuron 2579 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: 0.1233. Min Range: -0.1233

Max Act: 0.1233. Min Act: -0.0000

Data Index: 1604213 (The Pile)

Max Activating Token Index: 192

Text #1

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1109. Min Act: -0.0000

Data Index: 1008963 (The Pile)

Max Activating Token Index: 34

Text #2

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1206. Min Act: -0.0000

Data Index: 381663 (The Pile)

Max Activating Token Index: 63

Text #3

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1100. Min Act: -0.0000

Data Index: 368661 (The Pile)

Max Activating Token Index: 70

Text #4

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0982. Min Act: -0.0000

Data Index: 218860 (The Pile)

Max Activating Token Index: 6

Text #5

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1031. Min Act: -0.0000

Data Index: 532771 (The Pile)

Max Activating Token Index: 557

Text #6

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1085. Min Act: -0.0000

Data Index: 1954065 (The Pile)

Max Activating Token Index: 258

Text #7

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0968. Min Act: -0.0000

Data Index: 627942 (The Pile)

Max Activating Token Index: 195

Text #8

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0835. Min Act: -0.0000

Data Index: 1138294 (The Pile)

Max Activating Token Index: 695

Text #9

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1062. Min Act: -0.0000

Data Index: 1393635 (The Pile)

Max Activating Token Index: 25

Text #10

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1024. Min Act: -0.0000

Data Index: 1130237 (The Pile)

Max Activating Token Index: 340

Text #11

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1032. Min Act: -0.0000

Data Index: 81340 (The Pile)

Max Activating Token Index: 541

Text #12

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0959. Min Act: -0.0000

Data Index: 431954 (The Pile)

Max Activating Token Index: 498

Text #13

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1039. Min Act: -0.0000

Data Index: 425425 (The Pile)

Max Activating Token Index: 277

Text #14

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1038. Min Act: -0.0000

Data Index: 1452760 (The Pile)

Max Activating Token Index: 584

Text #15

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0974. Min Act: -0.0000

Data Index: 19758 (The Pile)

Max Activating Token Index: 217

Text #16

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1019. Min Act: -0.0000

Data Index: 164689 (The Pile)

Max Activating Token Index: 107

Text #17

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0991. Min Act: -0.0000

Data Index: 1583291 (The Pile)

Max Activating Token Index: 714

Text #18

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0938. Min Act: -0.0000

Data Index: 988638 (The Pile)

Max Activating Token Index: 507

Text #19

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0947. Min Act: -0.0000

Data Index: 1366176 (The Pile)

Max Activating Token Index: 170