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

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

Neuron 5076 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.3342. Min Range: -6.3342

Max Act: 6.3342. Min Act: -0.0000

Data Index: 875147 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 6.3342. Min Range: -6.3342

Max Act: 6.1602. Min Act: -0.0000

Data Index: 1048171 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 6.3342. Min Range: -6.3342

Max Act: 5.5425. Min Act: -0.0000

Data Index: 302226 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 6.3342. Min Range: -6.3342

Max Act: 5.9875. Min Act: -0.0000

Data Index: 1362453 (Python Code)

Max Activating Token Index: 244

Text #4

Max Range: 6.3342. Min Range: -6.3342

Max Act: 5.9476. Min Act: -0.0000

Data Index: 503666 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 6.3342. Min Range: -6.3342

Max Act: 5.8454. Min Act: -0.0000

Data Index: 831101 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 6.3342. Min Range: -6.3342

Max Act: 5.9862. Min Act: -0.0000

Data Index: 1106373 (C4 (Web Text))

Max Activating Token Index: 997

Text #7

Max Range: 6.3342. Min Range: -6.3342

Max Act: 5.7984. Min Act: -0.0000

Data Index: 897931 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 6.3342. Min Range: -6.3342

Max Act: 5.6394. Min Act: -0.0000

Data Index: 474612 (C4 (Web Text))

Max Activating Token Index: 417

Text #9

Max Range: 6.3342. Min Range: -6.3342

Max Act: 5.4448. Min Act: -0.0000

Data Index: 202707 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 6.3342. Min Range: -6.3342

Max Act: 5.6460. Min Act: -0.0000

Data Index: 1187154 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 6.3342. Min Range: -6.3342

Max Act: 5.4215. Min Act: -0.0000

Data Index: 134870 (C4 (Web Text))

Max Activating Token Index: 107

Text #12

Max Range: 6.3342. Min Range: -6.3342

Max Act: 5.4281. Min Act: -0.0000

Data Index: 1005426 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 6.3342. Min Range: -6.3342

Max Act: 5.5831. Min Act: -0.0000

Data Index: 123340 (C4 (Web Text))

Max Activating Token Index: 303

Text #14

Max Range: 6.3342. Min Range: -6.3342

Max Act: 5.5609. Min Act: -0.0000

Data Index: 1608973 (Python Code)

Max Activating Token Index: 752

Text #15

Max Range: 6.3342. Min Range: -6.3342

Max Act: 5.5717. Min Act: -0.0000

Data Index: 283731 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 6.3342. Min Range: -6.3342

Max Act: 5.3292. Min Act: -0.0000

Data Index: 618804 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 6.3342. Min Range: -6.3342

Max Act: 5.4891. Min Act: -0.0000

Data Index: 52912 (C4 (Web Text))

Max Activating Token Index: 96

Text #18

Max Range: 6.3342. Min Range: -6.3342

Max Act: 5.2578. Min Act: -0.0000

Data Index: 1049326 (C4 (Web Text))

Max Activating Token Index: 409

Text #19

Max Range: 6.3342. Min Range: -6.3342

Max Act: 5.4414. Min Act: -0.0000

Data Index: 38367 (C4 (Web Text))

Max Activating Token Index: 487