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

Dataset: The Pile

Neuron 635 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6709. Min Range: -1.6709

Max Act: 1.6709. Min Act: -0.0000

Data Index: 1389929 (The Pile)

Max Activating Token Index: 615

Text #1

Max Range: 1.6709. Min Range: -1.6709

Max Act: 1.3081. Min Act: -0.0000

Data Index: 297517 (The Pile)

Max Activating Token Index: 596

Text #2

Max Range: 1.6709. Min Range: -1.6709

Max Act: 1.0537. Min Act: -0.0000

Data Index: 1326636 (The Pile)

Max Activating Token Index: 630

Text #3

Max Range: 1.6709. Min Range: -1.6709

Max Act: 1.2552. Min Act: -0.0000

Data Index: 801597 (The Pile)

Max Activating Token Index: 792

Text #4

Max Range: 1.6709. Min Range: -1.6709

Max Act: 1.1749. Min Act: -0.0000

Data Index: 167067 (The Pile)

Max Activating Token Index: 17

Text #5

Max Range: 1.6709. Min Range: -1.6709

Max Act: 1.2125. Min Act: -0.0000

Data Index: 209425 (The Pile)

Max Activating Token Index: 1014

Text #6

Max Range: 1.6709. Min Range: -1.6709

Max Act: 1.0425. Min Act: 0.0000

Data Index: 365904 (The Pile)

Max Activating Token Index: 210

Text #7

Max Range: 1.6709. Min Range: -1.6709

Max Act: 1.0031. Min Act: -0.0000

Data Index: 227386 (The Pile)

Max Activating Token Index: 1009

Text #8

Max Range: 1.6709. Min Range: -1.6709

Max Act: 1.0219. Min Act: -0.0000

Data Index: 1307823 (The Pile)

Max Activating Token Index: 678

Text #9

Max Range: 1.6709. Min Range: -1.6709

Max Act: 0.9960. Min Act: -0.0000

Data Index: 14156 (The Pile)

Max Activating Token Index: 502

Text #10

Max Range: 1.6709. Min Range: -1.6709

Max Act: 1.0311. Min Act: -0.0000

Data Index: 1736554 (The Pile)

Max Activating Token Index: 54

Text #11

Max Range: 1.6709. Min Range: -1.6709

Max Act: 0.9928. Min Act: -0.0000

Data Index: 1695487 (The Pile)

Max Activating Token Index: 263

Text #12

Max Range: 1.6709. Min Range: -1.6709

Max Act: 0.9854. Min Act: -0.0000

Data Index: 1026798 (The Pile)

Max Activating Token Index: 35

Text #13

Max Range: 1.6709. Min Range: -1.6709

Max Act: 0.9932. Min Act: -0.0000

Data Index: 1144671 (The Pile)

Max Activating Token Index: 1016

Text #14

Max Range: 1.6709. Min Range: -1.6709

Max Act: 0.9830. Min Act: -0.0000

Data Index: 534574 (The Pile)

Max Activating Token Index: 884

Text #15

Max Range: 1.6709. Min Range: -1.6709

Max Act: 0.9148. Min Act: -0.0000

Data Index: 1287564 (The Pile)

Max Activating Token Index: 296

Text #16

Max Range: 1.6709. Min Range: -1.6709

Max Act: 0.8887. Min Act: -0.0000

Data Index: 1109057 (The Pile)

Max Activating Token Index: 135

Text #17

Max Range: 1.6709. Min Range: -1.6709

Max Act: 0.7477. Min Act: -0.0000

Data Index: 1382755 (The Pile)

Max Activating Token Index: 666

Text #18

Max Range: 1.6709. Min Range: -1.6709

Max Act: 0.9364. Min Act: -0.0000

Data Index: 58992 (The Pile)

Max Activating Token Index: 932

Text #19

Max Range: 1.6709. Min Range: -1.6709

Max Act: 0.8964. Min Act: -0.0000

Data Index: 1151931 (The Pile)

Max Activating Token Index: 1009