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

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

Neuron 2769 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: 1.4420. Min Range: -1.4420

Max Act: 1.4420. Min Act: -0.0003

Data Index: 1009170 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 1.4420. Min Range: -1.4420

Max Act: 1.1015. Min Act: -0.0003

Data Index: 1033982 (C4 (Web Text))

Max Activating Token Index: 819

Text #2

Max Range: 1.4420. Min Range: -1.4420

Max Act: 0.9722. Min Act: -0.0002

Data Index: 1104682 (C4 (Web Text))

Max Activating Token Index: 971

Text #3

Max Range: 1.4420. Min Range: -1.4420

Max Act: 1.0283. Min Act: -0.0002

Data Index: 1354939 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 1.4420. Min Range: -1.4420

Max Act: 1.0922. Min Act: -0.0002

Data Index: 608422 (C4 (Web Text))

Max Activating Token Index: 972

Text #5

Max Range: 1.4420. Min Range: -1.4420

Max Act: 0.9613. Min Act: -0.0002

Data Index: 276998 (C4 (Web Text))

Max Activating Token Index: 231

Text #6

Max Range: 1.4420. Min Range: -1.4420

Max Act: 1.0777. Min Act: -0.0002

Data Index: 1085531 (C4 (Web Text))

Max Activating Token Index: 1015

Text #7

Max Range: 1.4420. Min Range: -1.4420

Max Act: 1.1012. Min Act: -0.0002

Data Index: 1118981 (C4 (Web Text))

Max Activating Token Index: 998

Text #8

Max Range: 1.4420. Min Range: -1.4420

Max Act: 0.9519. Min Act: -0.0002

Data Index: 584945 (C4 (Web Text))

Max Activating Token Index: 275

Text #9

Max Range: 1.4420. Min Range: -1.4420

Max Act: 1.0627. Min Act: -0.0002

Data Index: 889183 (C4 (Web Text))

Max Activating Token Index: 941

Text #10

Max Range: 1.4420. Min Range: -1.4420

Max Act: 0.8494. Min Act: -0.0002

Data Index: 1275782 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 1.4420. Min Range: -1.4420

Max Act: 0.9492. Min Act: -0.0002

Data Index: 1163520 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 1.4420. Min Range: -1.4420

Max Act: 0.9300. Min Act: -0.0002

Data Index: 1322584 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 1.4420. Min Range: -1.4420

Max Act: 0.9745. Min Act: -0.0002

Data Index: 543696 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 1.4420. Min Range: -1.4420

Max Act: 0.8429. Min Act: -0.0002

Data Index: 886202 (C4 (Web Text))

Max Activating Token Index: 368

Text #15

Max Range: 1.4420. Min Range: -1.4420

Max Act: 0.9618. Min Act: -0.0002

Data Index: 1107562 (C4 (Web Text))

Max Activating Token Index: 3

Text #16

Max Range: 1.4420. Min Range: -1.4420

Max Act: 0.9618. Min Act: -0.0002

Data Index: 533574 (C4 (Web Text))

Max Activating Token Index: 3

Text #17

Max Range: 1.4420. Min Range: -1.4420

Max Act: 0.9618. Min Act: -0.0002

Data Index: 839258 (C4 (Web Text))

Max Activating Token Index: 3

Text #18

Max Range: 1.4420. Min Range: -1.4420

Max Act: 0.9618. Min Act: -0.0002

Data Index: 147382 (C4 (Web Text))

Max Activating Token Index: 3

Text #19

Max Range: 1.4420. Min Range: -1.4420

Max Act: 0.9632. Min Act: -0.0002

Data Index: 1279194 (C4 (Web Text))

Max Activating Token Index: 966