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

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

Neuron 112 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0178. Min Range: -2.0178

Max Act: 1.9763. Min Act: -0.0000

Data Index: 455018 (C4 (Web Text))

Max Activating Token Index: 127

Text #1

Max Range: 2.0178. Min Range: -2.0178

Max Act: 1.9215. Min Act: -0.0000

Data Index: 294135 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 2.0178. Min Range: -2.0178

Max Act: 2.0178. Min Act: -0.0000

Data Index: 596436 (C4 (Web Text))

Max Activating Token Index: 162

Text #3

Max Range: 2.0178. Min Range: -2.0178

Max Act: 1.7770. Min Act: -0.0000

Data Index: 740451 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 2.0178. Min Range: -2.0178

Max Act: 1.8353. Min Act: -0.0000

Data Index: 759933 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 2.0178. Min Range: -2.0178

Max Act: 1.8193. Min Act: -0.0000

Data Index: 952865 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 2.0178. Min Range: -2.0178

Max Act: 1.6503. Min Act: -0.0000

Data Index: 896467 (C4 (Web Text))

Max Activating Token Index: 972

Text #7

Max Range: 2.0178. Min Range: -2.0178

Max Act: 1.6445. Min Act: -0.0000

Data Index: 1270864 (C4 (Web Text))

Max Activating Token Index: 3

Text #8

Max Range: 2.0178. Min Range: -2.0178

Max Act: 1.6520. Min Act: -0.0000

Data Index: 124984 (C4 (Web Text))

Max Activating Token Index: 999

Text #9

Max Range: 2.0178. Min Range: -2.0178

Max Act: 1.6596. Min Act: -0.0000

Data Index: 691748 (C4 (Web Text))

Max Activating Token Index: 588

Text #10

Max Range: 2.0178. Min Range: -2.0178

Max Act: 1.6520. Min Act: -0.0000

Data Index: 1313764 (C4 (Web Text))

Max Activating Token Index: 960

Text #11

Max Range: 2.0178. Min Range: -2.0178

Max Act: 1.6329. Min Act: -0.0000

Data Index: 59652 (C4 (Web Text))

Max Activating Token Index: 838

Text #12

Max Range: 2.0178. Min Range: -2.0178

Max Act: 1.5408. Min Act: -0.0000

Data Index: 676994 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 2.0178. Min Range: -2.0178

Max Act: 1.4542. Min Act: -0.0000

Data Index: 1159640 (C4 (Web Text))

Max Activating Token Index: 688

Text #14

Max Range: 2.0178. Min Range: -2.0178

Max Act: 1.5212. Min Act: -0.0000

Data Index: 447436 (C4 (Web Text))

Max Activating Token Index: 19

Text #15

Max Range: 2.0178. Min Range: -2.0178

Max Act: 1.4403. Min Act: -0.0000

Data Index: 1174653 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 2.0178. Min Range: -2.0178

Max Act: 1.5062. Min Act: 0.0000

Data Index: 604801 (C4 (Web Text))

Max Activating Token Index: 120

Text #17

Max Range: 2.0178. Min Range: -2.0178

Max Act: 1.5147. Min Act: -0.0000

Data Index: 850891 (C4 (Web Text))

Max Activating Token Index: 1017

Text #18

Max Range: 2.0178. Min Range: -2.0178

Max Act: 1.3454. Min Act: -0.0000

Data Index: 175236 (C4 (Web Text))

Max Activating Token Index: 478

Text #19

Max Range: 2.0178. Min Range: -2.0178

Max Act: 1.3996. Min Act: -0.0000

Data Index: 95137 (C4 (Web Text))

Max Activating Token Index: 897