Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 674 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0707. Min Act: -0.0003

Data Index: 803314 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0699. Min Act: -0.0003

Data Index: 1265187 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0659. Min Act: -0.0002

Data Index: 866272 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0659. Min Act: -0.0003

Data Index: 668491 (C4 (Web Text))

Max Activating Token Index: 647

Text #4

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0635. Min Act: -0.0003

Data Index: 1020261 (C4 (Web Text))

Max Activating Token Index: 177

Text #5

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0645. Min Act: -0.0003

Data Index: 1037127 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0629. Min Act: -0.0003

Data Index: 52628 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0647. Min Act: -0.0003

Data Index: 461286 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0645. Min Act: -0.0002

Data Index: 755779 (C4 (Web Text))

Max Activating Token Index: 601

Text #9

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0638. Min Act: -0.0003

Data Index: 985181 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0624. Min Act: -0.0003

Data Index: 122728 (C4 (Web Text))

Max Activating Token Index: 958

Text #11

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0636. Min Act: -0.0003

Data Index: 478246 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0631. Min Act: -0.0003

Data Index: 945592 (C4 (Web Text))

Max Activating Token Index: 265

Text #13

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0638. Min Act: -0.0003

Data Index: 669001 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0624. Min Act: -0.0003

Data Index: 555998 (C4 (Web Text))

Max Activating Token Index: 116

Text #15

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0613. Min Act: -0.0003

Data Index: 1124021 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0619. Min Act: -0.0003

Data Index: 990044 (C4 (Web Text))

Max Activating Token Index: 519

Text #17

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0631. Min Act: -0.0003

Data Index: 164856 (C4 (Web Text))

Max Activating Token Index: 487

Text #18

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0612. Min Act: -0.0003

Data Index: 1270855 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0622. Min Act: -0.0003

Data Index: 198318 (C4 (Web Text))

Max Activating Token Index: 1023