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

Dataset: The Pile

Neuron 690 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.6555. Min Act: -0.0000

Data Index: 1842223 (The Pile)

Max Activating Token Index: 349

Text #1

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.6686. Min Act: -0.0000

Data Index: 240535 (The Pile)

Max Activating Token Index: 25

Text #2

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.6054. Min Act: -0.0000

Data Index: 143989 (The Pile)

Max Activating Token Index: 875

Text #3

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.5922. Min Act: -0.0000

Data Index: 539703 (The Pile)

Max Activating Token Index: 235

Text #4

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.5401. Min Act: -0.0000

Data Index: 1615482 (The Pile)

Max Activating Token Index: 999

Text #5

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.5885. Min Act: -0.0000

Data Index: 1608270 (The Pile)

Max Activating Token Index: 1000

Text #6

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.5669. Min Act: -0.0000

Data Index: 889732 (The Pile)

Max Activating Token Index: 142

Text #7

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.5695. Min Act: -0.0000

Data Index: 1368494 (The Pile)

Max Activating Token Index: 865

Text #8

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.5436. Min Act: -0.0000

Data Index: 877228 (The Pile)

Max Activating Token Index: 795

Text #9

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.5179. Min Act: -0.0000

Data Index: 586066 (The Pile)

Max Activating Token Index: 949

Text #10

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.5487. Min Act: -0.0000

Data Index: 1982710 (The Pile)

Max Activating Token Index: 724

Text #11

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.5385. Min Act: -0.0000

Data Index: 1125661 (The Pile)

Max Activating Token Index: 239

Text #12

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.5592. Min Act: -0.0000

Data Index: 1148019 (The Pile)

Max Activating Token Index: 601

Text #13

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.4988. Min Act: -0.0000

Data Index: 1302086 (The Pile)

Max Activating Token Index: 866

Text #14

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.4861. Min Act: -0.0000

Data Index: 1184681 (The Pile)

Max Activating Token Index: 793

Text #15

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.5127. Min Act: -0.0000

Data Index: 323686 (The Pile)

Max Activating Token Index: 216

Text #16

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.5557. Min Act: -0.0000

Data Index: 671192 (The Pile)

Max Activating Token Index: 488

Text #17

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.5033. Min Act: -0.0000

Data Index: 275055 (The Pile)

Max Activating Token Index: 1007

Text #18

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.4809. Min Act: -0.0000

Data Index: 1493994 (The Pile)

Max Activating Token Index: 902

Text #19

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.4953. Min Act: -0.0000

Data Index: 1640162 (The Pile)

Max Activating Token Index: 95