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

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

Neuron 4298 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1545. Min Act: -0.0000

Data Index: 517644 (C4 (Web Text))

Max Activating Token Index: 421

Text #1

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1262. Min Act: -0.0000

Data Index: 282478 (C4 (Web Text))

Max Activating Token Index: 480

Text #2

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1125. Min Act: -0.0000

Data Index: 659683 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1074. Min Act: -0.0000

Data Index: 137930 (C4 (Web Text))

Max Activating Token Index: 676

Text #4

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1033. Min Act: -0.0000

Data Index: 925304 (C4 (Web Text))

Max Activating Token Index: 654

Text #5

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1069. Min Act: -0.0000

Data Index: 283292 (C4 (Web Text))

Max Activating Token Index: 262

Text #6

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1113. Min Act: 0.0000

Data Index: 1041616 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1018. Min Act: 0.0000

Data Index: 1141984 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.0973. Min Act: -0.0000

Data Index: 277875 (C4 (Web Text))

Max Activating Token Index: 943

Text #9

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1021. Min Act: -0.0000

Data Index: 280560 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.0999. Min Act: -0.0000

Data Index: 1193873 (C4 (Web Text))

Max Activating Token Index: 484

Text #11

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.0989. Min Act: -0.0000

Data Index: 725382 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.0981. Min Act: 0.0000

Data Index: 940370 (C4 (Web Text))

Max Activating Token Index: 489

Text #13

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.0988. Min Act: 0.0000

Data Index: 178159 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.0977. Min Act: 0.0000

Data Index: 204408 (C4 (Web Text))

Max Activating Token Index: 181

Text #15

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.0935. Min Act: -0.0000

Data Index: 63439 (C4 (Web Text))

Max Activating Token Index: 132

Text #16

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1006. Min Act: -0.0000

Data Index: 509593 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.0967. Min Act: -0.0000

Data Index: 67834 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.0931. Min Act: -0.0000

Data Index: 94364 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.0953. Min Act: 0.0000

Data Index: 886837 (C4 (Web Text))

Max Activating Token Index: 735