Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 197 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0547. Min Act: -0.0002

Data Index: 1468535 (Python Code)

Max Activating Token Index: 816

Text #1

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0550. Min Act: -0.0002

Data Index: 918534 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0482. Min Act: -0.0002

Data Index: 776433 (C4 (Web Text))

Max Activating Token Index: 331

Text #3

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0471. Min Act: -0.0002

Data Index: 243018 (C4 (Web Text))

Max Activating Token Index: 964

Text #4

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0447. Min Act: -0.0002

Data Index: 260438 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0434. Min Act: -0.0002

Data Index: 609930 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0429. Min Act: -0.0002

Data Index: 1249250 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0439. Min Act: -0.0002

Data Index: 1590911 (Python Code)

Max Activating Token Index: 562

Text #8

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0422. Min Act: -0.0002

Data Index: 1524105 (Python Code)

Max Activating Token Index: 979

Text #9

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0431. Min Act: -0.0002

Data Index: 1323648 (C4 (Web Text))

Max Activating Token Index: 446

Text #10

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0430. Min Act: -0.0002

Data Index: 768370 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0424. Min Act: -0.0002

Data Index: 269465 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0414. Min Act: -0.0002

Data Index: 622679 (C4 (Web Text))

Max Activating Token Index: 459

Text #13

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0376. Min Act: -0.0002

Data Index: 859114 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0417. Min Act: -0.0002

Data Index: 625000 (C4 (Web Text))

Max Activating Token Index: 102

Text #15

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0421. Min Act: -0.0002

Data Index: 893845 (C4 (Web Text))

Max Activating Token Index: 622

Text #16

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0406. Min Act: -0.0002

Data Index: 1104236 (C4 (Web Text))

Max Activating Token Index: 110

Text #17

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0414. Min Act: -0.0002

Data Index: 112400 (C4 (Web Text))

Max Activating Token Index: 519

Text #18

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0406. Min Act: -0.0002

Data Index: 89480 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0346. Min Act: -0.0002

Data Index: 18240 (C4 (Web Text))

Max Activating Token Index: 1013