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

Dataset: The Pile

Neuron 2718 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1138. Min Range: -3.1138

Max Act: 3.1138. Min Act: -0.0000

Data Index: 987626 (The Pile)

Max Activating Token Index: 827

Text #1

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.5756. Min Act: -0.0000

Data Index: 1958621 (The Pile)

Max Activating Token Index: 876

Text #2

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.6563. Min Act: -0.0000

Data Index: 724233 (The Pile)

Max Activating Token Index: 73

Text #3

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.6155. Min Act: -0.0000

Data Index: 1343715 (The Pile)

Max Activating Token Index: 368

Text #4

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.6103. Min Act: -0.0000

Data Index: 1190752 (The Pile)

Max Activating Token Index: 769

Text #5

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.5430. Min Act: -0.0000

Data Index: 1707617 (The Pile)

Max Activating Token Index: 238

Text #6

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.6890. Min Act: -0.0000

Data Index: 184377 (The Pile)

Max Activating Token Index: 676

Text #7

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.5342. Min Act: -0.0000

Data Index: 737136 (The Pile)

Max Activating Token Index: 956

Text #8

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.5278. Min Act: -0.0000

Data Index: 1194655 (The Pile)

Max Activating Token Index: 937

Text #9

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.5203. Min Act: -0.0000

Data Index: 377303 (The Pile)

Max Activating Token Index: 960

Text #10

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.3199. Min Act: -0.0000

Data Index: 1211470 (The Pile)

Max Activating Token Index: 993

Text #11

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.4548. Min Act: -0.0000

Data Index: 661286 (The Pile)

Max Activating Token Index: 88

Text #12

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.4052. Min Act: -0.0000

Data Index: 125457 (The Pile)

Max Activating Token Index: 399

Text #13

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.4070. Min Act: -0.0000

Data Index: 929608 (The Pile)

Max Activating Token Index: 345

Text #14

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.5116. Min Act: -0.0000

Data Index: 1916073 (The Pile)

Max Activating Token Index: 60

Text #15

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.2794. Min Act: -0.0000

Data Index: 1107386 (The Pile)

Max Activating Token Index: 670

Text #16

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.3760. Min Act: -0.0000

Data Index: 445193 (The Pile)

Max Activating Token Index: 893

Text #17

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.3566. Min Act: -0.0000

Data Index: 1893657 (The Pile)

Max Activating Token Index: 98

Text #18

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.3342. Min Act: -0.0000

Data Index: 1303743 (The Pile)

Max Activating Token Index: 878

Text #19

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.3307. Min Act: -0.0000

Data Index: 340883 (The Pile)

Max Activating Token Index: 604