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

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

Neuron 2401 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1562. Min Range: -1.1562

Max Act: 1.1562. Min Act: -0.0000

Data Index: 942755 (C4 (Web Text))

Max Activating Token Index: 227

Text #1

Max Range: 1.1562. Min Range: -1.1562

Max Act: 1.0028. Min Act: -0.0000

Data Index: 76302 (C4 (Web Text))

Max Activating Token Index: 436

Text #2

Max Range: 1.1562. Min Range: -1.1562

Max Act: 0.9478. Min Act: -0.0000

Data Index: 1267488 (C4 (Web Text))

Max Activating Token Index: 733

Text #3

Max Range: 1.1562. Min Range: -1.1562

Max Act: 0.9160. Min Act: -0.0000

Data Index: 717272 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 1.1562. Min Range: -1.1562

Max Act: 0.8714. Min Act: -0.0000

Data Index: 725126 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 1.1562. Min Range: -1.1562

Max Act: 0.8870. Min Act: -0.0000

Data Index: 1217555 (C4 (Web Text))

Max Activating Token Index: 618

Text #6

Max Range: 1.1562. Min Range: -1.1562

Max Act: 0.8119. Min Act: -0.0000

Data Index: 1575074 (Python Code)

Max Activating Token Index: 294

Text #7

Max Range: 1.1562. Min Range: -1.1562

Max Act: 0.7831. Min Act: -0.0000

Data Index: 1198170 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 1.1562. Min Range: -1.1562

Max Act: 0.7595. Min Act: -0.0000

Data Index: 887614 (C4 (Web Text))

Max Activating Token Index: 507

Text #9

Max Range: 1.1562. Min Range: -1.1562

Max Act: 0.7341. Min Act: -0.0000

Data Index: 112141 (C4 (Web Text))

Max Activating Token Index: 987

Text #10

Max Range: 1.1562. Min Range: -1.1562

Max Act: 0.7544. Min Act: -0.0000

Data Index: 255360 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 1.1562. Min Range: -1.1562

Max Act: 0.7748. Min Act: -0.0000

Data Index: 1006071 (C4 (Web Text))

Max Activating Token Index: 822

Text #12

Max Range: 1.1562. Min Range: -1.1562

Max Act: 0.7389. Min Act: -0.0000

Data Index: 1104146 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 1.1562. Min Range: -1.1562

Max Act: 0.7012. Min Act: -0.0000

Data Index: 516957 (C4 (Web Text))

Max Activating Token Index: 367

Text #14

Max Range: 1.1562. Min Range: -1.1562

Max Act: 0.6815. Min Act: -0.0000

Data Index: 700342 (C4 (Web Text))

Max Activating Token Index: 891

Text #15

Max Range: 1.1562. Min Range: -1.1562

Max Act: 0.6366. Min Act: -0.0000

Data Index: 36809 (C4 (Web Text))

Max Activating Token Index: 979

Text #16

Max Range: 1.1562. Min Range: -1.1562

Max Act: 0.7396. Min Act: -0.0000

Data Index: 647545 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 1.1562. Min Range: -1.1562

Max Act: 0.7236. Min Act: -0.0000

Data Index: 855115 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 1.1562. Min Range: -1.1562

Max Act: 0.6743. Min Act: -0.0000

Data Index: 830466 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 1.1562. Min Range: -1.1562

Max Act: 0.7124. Min Act: -0.0000

Data Index: 128153 (C4 (Web Text))

Max Activating Token Index: 559