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

Dataset: The Pile

Neuron 1811 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: 1.9283. Min Range: -1.9283

Max Act: 1.9283. Min Act: -0.0000

Data Index: 1502949 (The Pile)

Max Activating Token Index: 933

Text #1

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.8897. Min Act: -0.0000

Data Index: 1338465 (The Pile)

Max Activating Token Index: 391

Text #2

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.7691. Min Act: -0.0000

Data Index: 1028717 (The Pile)

Max Activating Token Index: 128

Text #3

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.4284. Min Act: -0.0000

Data Index: 1871303 (The Pile)

Max Activating Token Index: 931

Text #4

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.5106. Min Act: -0.0000

Data Index: 1009545 (The Pile)

Max Activating Token Index: 91

Text #5

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.3562. Min Act: -0.0000

Data Index: 500825 (The Pile)

Max Activating Token Index: 842

Text #6

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.3177. Min Act: -0.0000

Data Index: 1601566 (The Pile)

Max Activating Token Index: 532

Text #7

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.2884. Min Act: -0.0000

Data Index: 127796 (The Pile)

Max Activating Token Index: 719

Text #8

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.2573. Min Act: -0.0000

Data Index: 673227 (The Pile)

Max Activating Token Index: 498

Text #9

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.2670. Min Act: -0.0000

Data Index: 1190927 (The Pile)

Max Activating Token Index: 761

Text #10

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.1646. Min Act: -0.0000

Data Index: 429212 (The Pile)

Max Activating Token Index: 520

Text #11

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.3279. Min Act: -0.0000

Data Index: 1941014 (The Pile)

Max Activating Token Index: 694

Text #12

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.2603. Min Act: -0.0000

Data Index: 1931110 (The Pile)

Max Activating Token Index: 891

Text #13

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.3148. Min Act: -0.0000

Data Index: 415844 (The Pile)

Max Activating Token Index: 194

Text #14

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.2759. Min Act: -0.0000

Data Index: 606658 (The Pile)

Max Activating Token Index: 1000

Text #15

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.2736. Min Act: -0.0000

Data Index: 1651014 (The Pile)

Max Activating Token Index: 691

Text #16

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.1467. Min Act: -0.0000

Data Index: 1557181 (The Pile)

Max Activating Token Index: 61

Text #17

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.1233. Min Act: -0.0000

Data Index: 1185104 (The Pile)

Max Activating Token Index: 148

Text #18

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.1798. Min Act: -0.0000

Data Index: 1481849 (The Pile)

Max Activating Token Index: 950

Text #19

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.1977. Min Act: -0.0000

Data Index: 1224028 (The Pile)

Max Activating Token Index: 106