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

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

Neuron 3939 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: 1.3176. Min Range: -1.3176

Max Act: 1.2168. Min Act: -0.0000

Data Index: 103493 (C4 (Web Text))

Max Activating Token Index: 818

Text #1

Max Range: 1.3176. Min Range: -1.3176

Max Act: 1.2904. Min Act: -0.0000

Data Index: 298049 (C4 (Web Text))

Max Activating Token Index: 352

Text #2

Max Range: 1.3176. Min Range: -1.3176

Max Act: 1.2581. Min Act: -0.0000

Data Index: 174043 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 1.3176. Min Range: -1.3176

Max Act: 1.3176. Min Act: -0.0000

Data Index: 81890 (C4 (Web Text))

Max Activating Token Index: 955

Text #4

Max Range: 1.3176. Min Range: -1.3176

Max Act: 1.1617. Min Act: -0.0000

Data Index: 323603 (C4 (Web Text))

Max Activating Token Index: 306

Text #5

Max Range: 1.3176. Min Range: -1.3176

Max Act: 1.1809. Min Act: -0.0000

Data Index: 812769 (C4 (Web Text))

Max Activating Token Index: 465

Text #6

Max Range: 1.3176. Min Range: -1.3176

Max Act: 1.1655. Min Act: -0.0000

Data Index: 623649 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 1.3176. Min Range: -1.3176

Max Act: 1.1402. Min Act: -0.0000

Data Index: 1042862 (C4 (Web Text))

Max Activating Token Index: 932

Text #8

Max Range: 1.3176. Min Range: -1.3176

Max Act: 1.1505. Min Act: -0.0000

Data Index: 194363 (C4 (Web Text))

Max Activating Token Index: 875

Text #9

Max Range: 1.3176. Min Range: -1.3176

Max Act: 1.0513. Min Act: -0.0000

Data Index: 965081 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 1.3176. Min Range: -1.3176

Max Act: 1.1041. Min Act: -0.0000

Data Index: 534129 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 1.3176. Min Range: -1.3176

Max Act: 1.1013. Min Act: -0.0000

Data Index: 1011485 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 1.3176. Min Range: -1.3176

Max Act: 1.0703. Min Act: -0.0000

Data Index: 1406806 (Python Code)

Max Activating Token Index: 149

Text #13

Max Range: 1.3176. Min Range: -1.3176

Max Act: 1.0917. Min Act: -0.0000

Data Index: 96254 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 1.3176. Min Range: -1.3176

Max Act: 1.1085. Min Act: -0.0000

Data Index: 1028503 (C4 (Web Text))

Max Activating Token Index: 449

Text #15

Max Range: 1.3176. Min Range: -1.3176

Max Act: 1.1001. Min Act: -0.0000

Data Index: 640853 (C4 (Web Text))

Max Activating Token Index: 728

Text #16

Max Range: 1.3176. Min Range: -1.3176

Max Act: 1.0770. Min Act: -0.0000

Data Index: 1273589 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 1.3176. Min Range: -1.3176

Max Act: 1.0688. Min Act: -0.0000

Data Index: 1546028 (Python Code)

Max Activating Token Index: 479

Text #18

Max Range: 1.3176. Min Range: -1.3176

Max Act: 1.0677. Min Act: -0.0000

Data Index: 1046265 (C4 (Web Text))

Max Activating Token Index: 587

Text #19

Max Range: 1.3176. Min Range: -1.3176

Max Act: 1.0920. Min Act: -0.0000

Data Index: 1640648 (Python Code)

Max Activating Token Index: 335