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

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

Neuron 2590 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: 0.7722. Min Range: -0.7722

Max Act: 0.7722. Min Act: -0.0002

Data Index: 398725 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 0.7722. Min Range: -0.7722

Max Act: 0.7151. Min Act: -0.0002

Data Index: 1069153 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 0.7722. Min Range: -0.7722

Max Act: 0.7394. Min Act: -0.0002

Data Index: 525724 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 0.7722. Min Range: -0.7722

Max Act: 0.6959. Min Act: -0.0002

Data Index: 1135641 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 0.7722. Min Range: -0.7722

Max Act: 0.6632. Min Act: -0.0002

Data Index: 1095384 (C4 (Web Text))

Max Activating Token Index: 571

Text #5

Max Range: 0.7722. Min Range: -0.7722

Max Act: 0.7236. Min Act: -0.0002

Data Index: 1235795 (C4 (Web Text))

Max Activating Token Index: 441

Text #6

Max Range: 0.7722. Min Range: -0.7722

Max Act: 0.6192. Min Act: -0.0002

Data Index: 1108044 (C4 (Web Text))

Max Activating Token Index: 259

Text #7

Max Range: 0.7722. Min Range: -0.7722

Max Act: 0.6701. Min Act: -0.0002

Data Index: 434653 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 0.7722. Min Range: -0.7722

Max Act: 0.7042. Min Act: -0.0002

Data Index: 882529 (C4 (Web Text))

Max Activating Token Index: 587

Text #9

Max Range: 0.7722. Min Range: -0.7722

Max Act: 0.6361. Min Act: -0.0002

Data Index: 871257 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 0.7722. Min Range: -0.7722

Max Act: 0.6304. Min Act: -0.0002

Data Index: 140305 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 0.7722. Min Range: -0.7722

Max Act: 0.6048. Min Act: -0.0002

Data Index: 923809 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 0.7722. Min Range: -0.7722

Max Act: 0.6183. Min Act: -0.0002

Data Index: 963095 (C4 (Web Text))

Max Activating Token Index: 584

Text #13

Max Range: 0.7722. Min Range: -0.7722

Max Act: 0.5840. Min Act: -0.0002

Data Index: 1146474 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 0.7722. Min Range: -0.7722

Max Act: 0.6022. Min Act: -0.0002

Data Index: 64934 (C4 (Web Text))

Max Activating Token Index: 892

Text #15

Max Range: 0.7722. Min Range: -0.7722

Max Act: 0.5637. Min Act: -0.0002

Data Index: 81595 (C4 (Web Text))

Max Activating Token Index: 287

Text #16

Max Range: 0.7722. Min Range: -0.7722

Max Act: 0.5190. Min Act: -0.0002

Data Index: 1266657 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 0.7722. Min Range: -0.7722

Max Act: 0.5231. Min Act: -0.0002

Data Index: 349172 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 0.7722. Min Range: -0.7722

Max Act: 0.5247. Min Act: -0.0002

Data Index: 669348 (C4 (Web Text))

Max Activating Token Index: 239

Text #19

Max Range: 0.7722. Min Range: -0.7722

Max Act: 0.5526. Min Act: -0.0002

Data Index: 1159009 (C4 (Web Text))

Max Activating Token Index: 178