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

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

Neuron 1129 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: 0.3792. Min Range: -0.3792

Max Act: 0.3792. Min Act: -0.0000

Data Index: 791070 (C4 (Web Text))

Max Activating Token Index: 439

Text #1

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.3450. Min Act: -0.0000

Data Index: 493232 (C4 (Web Text))

Max Activating Token Index: 525

Text #2

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.3770. Min Act: -0.0000

Data Index: 770837 (C4 (Web Text))

Max Activating Token Index: 527

Text #3

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.3405. Min Act: -0.0000

Data Index: 1145071 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.3066. Min Act: -0.0000

Data Index: 1609437 (Python Code)

Max Activating Token Index: 606

Text #5

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.2893. Min Act: -0.0000

Data Index: 1578383 (Python Code)

Max Activating Token Index: 801

Text #6

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.3393. Min Act: -0.0000

Data Index: 1290701 (C4 (Web Text))

Max Activating Token Index: 781

Text #7

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.3257. Min Act: -0.0000

Data Index: 186736 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.3282. Min Act: -0.0000

Data Index: 767166 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.3284. Min Act: -0.0000

Data Index: 754393 (C4 (Web Text))

Max Activating Token Index: 261

Text #10

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.3073. Min Act: -0.0000

Data Index: 1363843 (Python Code)

Max Activating Token Index: 523

Text #11

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.3036. Min Act: -0.0000

Data Index: 363106 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.3226. Min Act: -0.0000

Data Index: 1466522 (Python Code)

Max Activating Token Index: 902

Text #13

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.2867. Min Act: -0.0000

Data Index: 384120 (C4 (Web Text))

Max Activating Token Index: 668

Text #14

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.2856. Min Act: -0.0000

Data Index: 1482854 (Python Code)

Max Activating Token Index: 286

Text #15

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.2885. Min Act: -0.0000

Data Index: 1521823 (Python Code)

Max Activating Token Index: 490

Text #16

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.2792. Min Act: -0.0000

Data Index: 28133 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.2673. Min Act: -0.0000

Data Index: 578558 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.2689. Min Act: -0.0000

Data Index: 1328924 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.2705. Min Act: -0.0000

Data Index: 1200428 (C4 (Web Text))

Max Activating Token Index: 52