Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4526 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7132. Min Range: -1.7132

Max Act: 1.7132. Min Act: -0.0000

Data Index: 548360 (C4 (Web Text))

Max Activating Token Index: 992

Text #1

Max Range: 1.7132. Min Range: -1.7132

Max Act: 1.5115. Min Act: -0.0000

Data Index: 1139406 (C4 (Web Text))

Max Activating Token Index: 238

Text #2

Max Range: 1.7132. Min Range: -1.7132

Max Act: 1.3591. Min Act: -0.0000

Data Index: 643676 (C4 (Web Text))

Max Activating Token Index: 426

Text #3

Max Range: 1.7132. Min Range: -1.7132

Max Act: 1.2743. Min Act: -0.0000

Data Index: 525851 (C4 (Web Text))

Max Activating Token Index: 396

Text #4

Max Range: 1.7132. Min Range: -1.7132

Max Act: 1.4342. Min Act: -0.0000

Data Index: 1122734 (C4 (Web Text))

Max Activating Token Index: 802

Text #5

Max Range: 1.7132. Min Range: -1.7132

Max Act: 1.3232. Min Act: -0.0000

Data Index: 549159 (C4 (Web Text))

Max Activating Token Index: 220

Text #6

Max Range: 1.7132. Min Range: -1.7132

Max Act: 1.1990. Min Act: -0.0000

Data Index: 522683 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 1.7132. Min Range: -1.7132

Max Act: 1.2495. Min Act: -0.0000

Data Index: 140814 (C4 (Web Text))

Max Activating Token Index: 720

Text #8

Max Range: 1.7132. Min Range: -1.7132

Max Act: 1.4073. Min Act: -0.0000

Data Index: 591433 (C4 (Web Text))

Max Activating Token Index: 891

Text #9

Max Range: 1.7132. Min Range: -1.7132

Max Act: 1.2415. Min Act: -0.0000

Data Index: 897268 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 1.7132. Min Range: -1.7132

Max Act: 1.1642. Min Act: -0.0000

Data Index: 768066 (C4 (Web Text))

Max Activating Token Index: 917

Text #11

Max Range: 1.7132. Min Range: -1.7132

Max Act: 1.0817. Min Act: -0.0000

Data Index: 1255282 (C4 (Web Text))

Max Activating Token Index: 1010

Text #12

Max Range: 1.7132. Min Range: -1.7132

Max Act: 1.2160. Min Act: -0.0000

Data Index: 1128180 (C4 (Web Text))

Max Activating Token Index: 95

Text #13

Max Range: 1.7132. Min Range: -1.7132

Max Act: 1.1967. Min Act: -0.0000

Data Index: 1268672 (C4 (Web Text))

Max Activating Token Index: 391

Text #14

Max Range: 1.7132. Min Range: -1.7132

Max Act: 1.1055. Min Act: -0.0000

Data Index: 702688 (C4 (Web Text))

Max Activating Token Index: 653

Text #15

Max Range: 1.7132. Min Range: -1.7132

Max Act: 1.3058. Min Act: -0.0000

Data Index: 332592 (C4 (Web Text))

Max Activating Token Index: 188

Text #16

Max Range: 1.7132. Min Range: -1.7132

Max Act: 1.1730. Min Act: -0.0000

Data Index: 1207884 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 1.7132. Min Range: -1.7132

Max Act: 1.2045. Min Act: -0.0000

Data Index: 1248426 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 1.7132. Min Range: -1.7132

Max Act: 1.0582. Min Act: -0.0000

Data Index: 931531 (C4 (Web Text))

Max Activating Token Index: 494

Text #19

Max Range: 1.7132. Min Range: -1.7132

Max Act: 1.0430. Min Act: -0.0000

Data Index: 974428 (C4 (Web Text))

Max Activating Token Index: 105