Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2102 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0582. Min Range: -0.0582

Max Act: 0.0574. Min Act: -0.0002

Data Index: 396689 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 0.0582. Min Range: -0.0582

Max Act: 0.0582. Min Act: -0.0002

Data Index: 191988 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 0.0582. Min Range: -0.0582

Max Act: 0.0523. Min Act: -0.0002

Data Index: 1272736 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 0.0582. Min Range: -0.0582

Max Act: 0.0502. Min Act: -0.0002

Data Index: 34493 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 0.0582. Min Range: -0.0582

Max Act: 0.0517. Min Act: -0.0002

Data Index: 717451 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 0.0582. Min Range: -0.0582

Max Act: 0.0514. Min Act: -0.0002

Data Index: 21200 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 0.0582. Min Range: -0.0582

Max Act: 0.0514. Min Act: -0.0002

Data Index: 219550 (C4 (Web Text))

Max Activating Token Index: 471

Text #7

Max Range: 0.0582. Min Range: -0.0582

Max Act: 0.0513. Min Act: -0.0002

Data Index: 478967 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 0.0582. Min Range: -0.0582

Max Act: 0.0502. Min Act: -0.0002

Data Index: 807155 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 0.0582. Min Range: -0.0582

Max Act: 0.0492. Min Act: -0.0002

Data Index: 284083 (C4 (Web Text))

Max Activating Token Index: 593

Text #10

Max Range: 0.0582. Min Range: -0.0582

Max Act: 0.0489. Min Act: -0.0002

Data Index: 1150411 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 0.0582. Min Range: -0.0582

Max Act: 0.0488. Min Act: -0.0002

Data Index: 478462 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 0.0582. Min Range: -0.0582

Max Act: 0.0483. Min Act: -0.0002

Data Index: 1277542 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 0.0582. Min Range: -0.0582

Max Act: 0.0473. Min Act: -0.0002

Data Index: 434706 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 0.0582. Min Range: -0.0582

Max Act: 0.0434. Min Act: -0.0002

Data Index: 222835 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 0.0582. Min Range: -0.0582

Max Act: 0.0453. Min Act: -0.0002

Data Index: 289784 (C4 (Web Text))

Max Activating Token Index: 919

Text #16

Max Range: 0.0582. Min Range: -0.0582

Max Act: 0.0440. Min Act: -0.0002

Data Index: 535349 (C4 (Web Text))

Max Activating Token Index: 79

Text #17

Max Range: 0.0582. Min Range: -0.0582

Max Act: 0.0454. Min Act: -0.0002

Data Index: 1130274 (C4 (Web Text))

Max Activating Token Index: 236

Text #18

Max Range: 0.0582. Min Range: -0.0582

Max Act: 0.0436. Min Act: -0.0002

Data Index: 264764 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 0.0582. Min Range: -0.0582

Max Act: 0.0466. Min Act: -0.0002

Data Index: 456906 (C4 (Web Text))

Max Activating Token Index: 827