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

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

Neuron 4394 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1333. Min Range: -2.1333

Max Act: 2.1333. Min Act: -0.0000

Data Index: 574020 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 2.1333. Min Range: -2.1333

Max Act: 1.8526. Min Act: -0.0000

Data Index: 918630 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 2.1333. Min Range: -2.1333

Max Act: 1.6501. Min Act: -0.0000

Data Index: 455281 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 2.1333. Min Range: -2.1333

Max Act: 1.6899. Min Act: -0.0000

Data Index: 266776 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 2.1333. Min Range: -2.1333

Max Act: 1.6833. Min Act: -0.0000

Data Index: 760593 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 2.1333. Min Range: -2.1333

Max Act: 1.5885. Min Act: -0.0000

Data Index: 716463 (C4 (Web Text))

Max Activating Token Index: 797

Text #6

Max Range: 2.1333. Min Range: -2.1333

Max Act: 1.5765. Min Act: -0.0000

Data Index: 1164438 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 2.1333. Min Range: -2.1333

Max Act: 1.5733. Min Act: -0.0000

Data Index: 1063047 (C4 (Web Text))

Max Activating Token Index: 1018

Text #8

Max Range: 2.1333. Min Range: -2.1333

Max Act: 1.5700. Min Act: -0.0000

Data Index: 432932 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 2.1333. Min Range: -2.1333

Max Act: 1.5649. Min Act: -0.0000

Data Index: 872816 (C4 (Web Text))

Max Activating Token Index: 817

Text #10

Max Range: 2.1333. Min Range: -2.1333

Max Act: 1.6066. Min Act: -0.0000

Data Index: 97404 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 2.1333. Min Range: -2.1333

Max Act: 1.4138. Min Act: -0.0001

Data Index: 682551 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 2.1333. Min Range: -2.1333

Max Act: 1.4589. Min Act: -0.0000

Data Index: 551444 (C4 (Web Text))

Max Activating Token Index: 284

Text #13

Max Range: 2.1333. Min Range: -2.1333

Max Act: 1.4105. Min Act: -0.0000

Data Index: 1195647 (C4 (Web Text))

Max Activating Token Index: 531

Text #14

Max Range: 2.1333. Min Range: -2.1333

Max Act: 1.6161. Min Act: -0.0000

Data Index: 119903 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 2.1333. Min Range: -2.1333

Max Act: 1.4790. Min Act: -0.0000

Data Index: 23635 (C4 (Web Text))

Max Activating Token Index: 765

Text #16

Max Range: 2.1333. Min Range: -2.1333

Max Act: 1.3117. Min Act: -0.0000

Data Index: 968958 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 2.1333. Min Range: -2.1333

Max Act: 1.4950. Min Act: -0.0000

Data Index: 870738 (C4 (Web Text))

Max Activating Token Index: 969

Text #18

Max Range: 2.1333. Min Range: -2.1333

Max Act: 1.4090. Min Act: -0.0000

Data Index: 87182 (C4 (Web Text))

Max Activating Token Index: 1011

Text #19

Max Range: 2.1333. Min Range: -2.1333

Max Act: 1.3718. Min Act: -0.0000

Data Index: 597814 (C4 (Web Text))

Max Activating Token Index: 934