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

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

Neuron 3730 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0219. Min Range: -5.0219

Max Act: 5.0219. Min Act: -0.0000

Data Index: 664483 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 5.0219. Min Range: -5.0219

Max Act: 4.3520. Min Act: -0.0000

Data Index: 338073 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 5.0219. Min Range: -5.0219

Max Act: 3.8803. Min Act: -0.0000

Data Index: 777419 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 5.0219. Min Range: -5.0219

Max Act: 3.7240. Min Act: -0.0000

Data Index: 214490 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 5.0219. Min Range: -5.0219

Max Act: 3.6001. Min Act: -0.0000

Data Index: 1309786 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 5.0219. Min Range: -5.0219

Max Act: 3.5660. Min Act: -0.0000

Data Index: 677557 (C4 (Web Text))

Max Activating Token Index: 865

Text #6

Max Range: 5.0219. Min Range: -5.0219

Max Act: 3.5541. Min Act: -0.0000

Data Index: 47253 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 5.0219. Min Range: -5.0219

Max Act: 3.5347. Min Act: -0.0000

Data Index: 1320098 (C4 (Web Text))

Max Activating Token Index: 447

Text #8

Max Range: 5.0219. Min Range: -5.0219

Max Act: 3.4726. Min Act: -0.0000

Data Index: 1190947 (C4 (Web Text))

Max Activating Token Index: 713

Text #9

Max Range: 5.0219. Min Range: -5.0219

Max Act: 3.4088. Min Act: -0.0000

Data Index: 1297357 (C4 (Web Text))

Max Activating Token Index: 184

Text #10

Max Range: 5.0219. Min Range: -5.0219

Max Act: 3.3777. Min Act: -0.0000

Data Index: 1096115 (C4 (Web Text))

Max Activating Token Index: 382

Text #11

Max Range: 5.0219. Min Range: -5.0219

Max Act: 3.2801. Min Act: -0.0000

Data Index: 1215336 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 5.0219. Min Range: -5.0219

Max Act: 3.2507. Min Act: -0.0000

Data Index: 272462 (C4 (Web Text))

Max Activating Token Index: 473

Text #13

Max Range: 5.0219. Min Range: -5.0219

Max Act: 3.0903. Min Act: -0.0000

Data Index: 864763 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 5.0219. Min Range: -5.0219

Max Act: 3.2225. Min Act: -0.0000

Data Index: 187632 (C4 (Web Text))

Max Activating Token Index: 1008

Text #15

Max Range: 5.0219. Min Range: -5.0219

Max Act: 3.0682. Min Act: -0.0000

Data Index: 1645156 (Python Code)

Max Activating Token Index: 193

Text #16

Max Range: 5.0219. Min Range: -5.0219

Max Act: 3.0389. Min Act: -0.0000

Data Index: 40536 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 5.0219. Min Range: -5.0219

Max Act: 3.1754. Min Act: -0.0000

Data Index: 200154 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 5.0219. Min Range: -5.0219

Max Act: 3.1632. Min Act: -0.0000

Data Index: 1635525 (Python Code)

Max Activating Token Index: 121

Text #19

Max Range: 5.0219. Min Range: -5.0219

Max Act: 2.9789. Min Act: -0.0000

Data Index: 814458 (C4 (Web Text))

Max Activating Token Index: 271