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

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

Neuron 19 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0546. Min Act: -0.0002

Data Index: 749780 (C4 (Web Text))

Max Activating Token Index: 673

Text #1

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0527. Min Act: -0.0002

Data Index: 1203735 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0515. Min Act: -0.0003

Data Index: 1057012 (C4 (Web Text))

Max Activating Token Index: 881

Text #3

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0488. Min Act: -0.0003

Data Index: 589760 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0462. Min Act: -0.0003

Data Index: 90253 (C4 (Web Text))

Max Activating Token Index: 661

Text #5

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0426. Min Act: -0.0002

Data Index: 93926 (C4 (Web Text))

Max Activating Token Index: 230

Text #6

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0462. Min Act: -0.0003

Data Index: 484694 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0454. Min Act: -0.0002

Data Index: 800968 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0453. Min Act: -0.0003

Data Index: 551153 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0443. Min Act: -0.0003

Data Index: 956679 (C4 (Web Text))

Max Activating Token Index: 95

Text #10

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0430. Min Act: -0.0003

Data Index: 541129 (C4 (Web Text))

Max Activating Token Index: 253

Text #11

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0422. Min Act: -0.0003

Data Index: 1125829 (C4 (Web Text))

Max Activating Token Index: 205

Text #12

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0418. Min Act: -0.0003

Data Index: 734065 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0413. Min Act: -0.0002

Data Index: 1150024 (C4 (Web Text))

Max Activating Token Index: 788

Text #14

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0414. Min Act: -0.0002

Data Index: 508094 (C4 (Web Text))

Max Activating Token Index: 364

Text #15

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0415. Min Act: -0.0002

Data Index: 840411 (C4 (Web Text))

Max Activating Token Index: 408

Text #16

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0426. Min Act: -0.0003

Data Index: 335670 (C4 (Web Text))

Max Activating Token Index: 947

Text #17

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0414. Min Act: -0.0002

Data Index: 897971 (C4 (Web Text))

Max Activating Token Index: 532

Text #18

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0408. Min Act: -0.0002

Data Index: 243716 (C4 (Web Text))

Max Activating Token Index: 637

Text #19

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0418. Min Act: -0.0002

Data Index: 1068766 (C4 (Web Text))

Max Activating Token Index: 497