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

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

Neuron 3385 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.8424. Min Act: -0.0000

Data Index: 703079 (C4 (Web Text))

Max Activating Token Index: 921

Text #1

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.8517. Min Act: -0.0000

Data Index: 78723 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.8207. Min Act: -0.0000

Data Index: 697162 (C4 (Web Text))

Max Activating Token Index: 756

Text #3

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.8127. Min Act: -0.0000

Data Index: 155023 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.7762. Min Act: -0.0000

Data Index: 946154 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.8231. Min Act: -0.0000

Data Index: 619428 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.7628. Min Act: -0.0000

Data Index: 767992 (C4 (Web Text))

Max Activating Token Index: 903

Text #7

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.7078. Min Act: -0.0000

Data Index: 376664 (C4 (Web Text))

Max Activating Token Index: 514

Text #8

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.7316. Min Act: -0.0000

Data Index: 263934 (C4 (Web Text))

Max Activating Token Index: 203

Text #9

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.7721. Min Act: -0.0000

Data Index: 142124 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.7645. Min Act: -0.0000

Data Index: 729812 (C4 (Web Text))

Max Activating Token Index: 282

Text #11

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.7382. Min Act: -0.0000

Data Index: 882811 (C4 (Web Text))

Max Activating Token Index: 551

Text #12

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.7253. Min Act: -0.0000

Data Index: 503869 (C4 (Web Text))

Max Activating Token Index: 684

Text #13

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.7399. Min Act: -0.0000

Data Index: 394757 (C4 (Web Text))

Max Activating Token Index: 796

Text #14

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.7147. Min Act: -0.0000

Data Index: 665863 (C4 (Web Text))

Max Activating Token Index: 556

Text #15

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.7058. Min Act: -0.0000

Data Index: 300180 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.7031. Min Act: -0.0000

Data Index: 10914 (C4 (Web Text))

Max Activating Token Index: 343

Text #17

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.6578. Min Act: -0.0000

Data Index: 906253 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.6935. Min Act: -0.0000

Data Index: 229804 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.6699. Min Act: -0.0000

Data Index: 485525 (C4 (Web Text))

Max Activating Token Index: 330