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

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

Neuron 575 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: 0.0502. Min Range: -0.0502

Max Act: 0.0501. Min Act: -0.0003

Data Index: 520570 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0501. Min Act: -0.0002

Data Index: 734215 (C4 (Web Text))

Max Activating Token Index: 640

Text #2

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0502. Min Act: -0.0004

Data Index: 1066463 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0481. Min Act: -0.0003

Data Index: 658174 (C4 (Web Text))

Max Activating Token Index: 1014

Text #4

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0468. Min Act: -0.0003

Data Index: 959209 (C4 (Web Text))

Max Activating Token Index: 417

Text #5

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0467. Min Act: -0.0001

Data Index: 714661 (C4 (Web Text))

Max Activating Token Index: 702

Text #6

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0453. Min Act: -0.0003

Data Index: 1044249 (C4 (Web Text))

Max Activating Token Index: 801

Text #7

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0460. Min Act: -0.0004

Data Index: 427373 (C4 (Web Text))

Max Activating Token Index: 330

Text #8

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0430. Min Act: -0.0003

Data Index: 546877 (C4 (Web Text))

Max Activating Token Index: 651

Text #9

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0442. Min Act: -0.0003

Data Index: 165696 (C4 (Web Text))

Max Activating Token Index: 408

Text #10

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0432. Min Act: -0.0003

Data Index: 1011532 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0435. Min Act: -0.0002

Data Index: 186974 (C4 (Web Text))

Max Activating Token Index: 310

Text #12

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0437. Min Act: -0.0003

Data Index: 999990 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0444. Min Act: -0.0003

Data Index: 945355 (C4 (Web Text))

Max Activating Token Index: 964

Text #14

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0427. Min Act: -0.0004

Data Index: 972335 (C4 (Web Text))

Max Activating Token Index: 962

Text #15

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0435. Min Act: -0.0003

Data Index: 1104361 (C4 (Web Text))

Max Activating Token Index: 517

Text #16

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0425. Min Act: -0.0004

Data Index: 1076962 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0435. Min Act: -0.0003

Data Index: 444778 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0424. Min Act: -0.0002

Data Index: 691385 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0430. Min Act: -0.0003

Data Index: 527032 (C4 (Web Text))

Max Activating Token Index: 710