Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3430 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 7.9127. Min Range: -7.9127

Max Act: 7.4829. Min Act: -0.0001

Data Index: 659220 (C4 (Web Text))

Max Activating Token Index: 83

Text #1

Max Range: 7.9127. Min Range: -7.9127

Max Act: 7.9127. Min Act: -0.0001

Data Index: 1323120 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 7.9127. Min Range: -7.9127

Max Act: 7.5695. Min Act: -0.0001

Data Index: 1135716 (C4 (Web Text))

Max Activating Token Index: 573

Text #3

Max Range: 7.9127. Min Range: -7.9127

Max Act: 7.3865. Min Act: -0.0001

Data Index: 9639 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 7.9127. Min Range: -7.9127

Max Act: 7.5423. Min Act: -0.0001

Data Index: 958654 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 7.9127. Min Range: -7.9127

Max Act: 7.3887. Min Act: -0.0001

Data Index: 944515 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 7.9127. Min Range: -7.9127

Max Act: 7.5310. Min Act: -0.0001

Data Index: 564608 (C4 (Web Text))

Max Activating Token Index: 763

Text #7

Max Range: 7.9127. Min Range: -7.9127

Max Act: 7.3699. Min Act: -0.0001

Data Index: 390779 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 7.9127. Min Range: -7.9127

Max Act: 7.3676. Min Act: -0.0001

Data Index: 478012 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 7.9127. Min Range: -7.9127

Max Act: 7.2269. Min Act: -0.0001

Data Index: 423145 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 7.9127. Min Range: -7.9127

Max Act: 7.2102. Min Act: -0.0001

Data Index: 821783 (C4 (Web Text))

Max Activating Token Index: 998

Text #11

Max Range: 7.9127. Min Range: -7.9127

Max Act: 7.1946. Min Act: -0.0001

Data Index: 417329 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 7.9127. Min Range: -7.9127

Max Act: 6.7932. Min Act: -0.0001

Data Index: 1174618 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 7.9127. Min Range: -7.9127

Max Act: 6.9576. Min Act: -0.0001

Data Index: 1169305 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 7.9127. Min Range: -7.9127

Max Act: 6.9376. Min Act: -0.0001

Data Index: 619076 (C4 (Web Text))

Max Activating Token Index: 587

Text #15

Max Range: 7.9127. Min Range: -7.9127

Max Act: 6.8699. Min Act: -0.0001

Data Index: 748450 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 7.9127. Min Range: -7.9127

Max Act: 6.7710. Min Act: -0.0001

Data Index: 158124 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 7.9127. Min Range: -7.9127

Max Act: 6.7776. Min Act: -0.0001

Data Index: 348280 (C4 (Web Text))

Max Activating Token Index: 827

Text #18

Max Range: 7.9127. Min Range: -7.9127

Max Act: 6.7727. Min Act: -0.0001

Data Index: 534978 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 7.9127. Min Range: -7.9127

Max Act: 6.7368. Min Act: -0.0001

Data Index: 69405 (C4 (Web Text))

Max Activating Token Index: 662