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

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

Neuron 4606 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1464. Min Act: -0.0002

Data Index: 277079 (C4 (Web Text))

Max Activating Token Index: 741

Text #1

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1391. Min Act: -0.0002

Data Index: 636638 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1311. Min Act: -0.0002

Data Index: 458243 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1388. Min Act: -0.0002

Data Index: 1298837 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1262. Min Act: -0.0002

Data Index: 674911 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1151. Min Act: -0.0002

Data Index: 834288 (C4 (Web Text))

Max Activating Token Index: 640

Text #6

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1335. Min Act: -0.0002

Data Index: 412328 (C4 (Web Text))

Max Activating Token Index: 714

Text #7

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1108. Min Act: -0.0002

Data Index: 1253854 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1225. Min Act: -0.0002

Data Index: 335080 (C4 (Web Text))

Max Activating Token Index: 679

Text #9

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1100. Min Act: -0.0002

Data Index: 1192859 (C4 (Web Text))

Max Activating Token Index: 369

Text #10

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1183. Min Act: -0.0002

Data Index: 1057738 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1183. Min Act: -0.0002

Data Index: 1009294 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1070. Min Act: -0.0002

Data Index: 795674 (C4 (Web Text))

Max Activating Token Index: 818

Text #13

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.0964. Min Act: -0.0002

Data Index: 982748 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1090. Min Act: -0.0002

Data Index: 1121583 (C4 (Web Text))

Max Activating Token Index: 80

Text #15

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1050. Min Act: -0.0002

Data Index: 644747 (C4 (Web Text))

Max Activating Token Index: 844

Text #16

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1078. Min Act: -0.0002

Data Index: 1076874 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1194. Min Act: -0.0002

Data Index: 1125024 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1010. Min Act: -0.0002

Data Index: 1529846 (Python Code)

Max Activating Token Index: 265

Text #19

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1056. Min Act: -0.0002

Data Index: 971984 (C4 (Web Text))

Max Activating Token Index: 268