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

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

Neuron 3778 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3673. Min Range: -3.3673

Max Act: 3.3673. Min Act: -0.0001

Data Index: 105544 (C4 (Web Text))

Max Activating Token Index: 844

Text #1

Max Range: 3.3673. Min Range: -3.3673

Max Act: 3.0085. Min Act: -0.0001

Data Index: 814893 (C4 (Web Text))

Max Activating Token Index: 921

Text #2

Max Range: 3.3673. Min Range: -3.3673

Max Act: 2.8941. Min Act: -0.0002

Data Index: 590806 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 3.3673. Min Range: -3.3673

Max Act: 2.7745. Min Act: -0.0002

Data Index: 771003 (C4 (Web Text))

Max Activating Token Index: 862

Text #4

Max Range: 3.3673. Min Range: -3.3673

Max Act: 2.6915. Min Act: -0.0001

Data Index: 1085913 (C4 (Web Text))

Max Activating Token Index: 131

Text #5

Max Range: 3.3673. Min Range: -3.3673

Max Act: 2.7104. Min Act: -0.0002

Data Index: 470448 (C4 (Web Text))

Max Activating Token Index: 919

Text #6

Max Range: 3.3673. Min Range: -3.3673

Max Act: 2.6704. Min Act: -0.0002

Data Index: 227362 (C4 (Web Text))

Max Activating Token Index: 28

Text #7

Max Range: 3.3673. Min Range: -3.3673

Max Act: 2.6659. Min Act: -0.0001

Data Index: 548011 (C4 (Web Text))

Max Activating Token Index: 408

Text #8

Max Range: 3.3673. Min Range: -3.3673

Max Act: 2.6606. Min Act: -0.0002

Data Index: 909054 (C4 (Web Text))

Max Activating Token Index: 956

Text #9

Max Range: 3.3673. Min Range: -3.3673

Max Act: 2.5010. Min Act: -0.0002

Data Index: 213781 (C4 (Web Text))

Max Activating Token Index: 925

Text #10

Max Range: 3.3673. Min Range: -3.3673

Max Act: 2.4252. Min Act: -0.0001

Data Index: 264195 (C4 (Web Text))

Max Activating Token Index: 647

Text #11

Max Range: 3.3673. Min Range: -3.3673

Max Act: 2.4994. Min Act: -0.0002

Data Index: 1312923 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 3.3673. Min Range: -3.3673

Max Act: 2.4868. Min Act: -0.0001

Data Index: 1009249 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 3.3673. Min Range: -3.3673

Max Act: 2.4841. Min Act: -0.0001

Data Index: 1205989 (C4 (Web Text))

Max Activating Token Index: 486

Text #14

Max Range: 3.3673. Min Range: -3.3673

Max Act: 2.5552. Min Act: -0.0002

Data Index: 1347908 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 3.3673. Min Range: -3.3673

Max Act: 2.5409. Min Act: -0.0002

Data Index: 538224 (C4 (Web Text))

Max Activating Token Index: 654

Text #16

Max Range: 3.3673. Min Range: -3.3673

Max Act: 2.4049. Min Act: -0.0002

Data Index: 22399 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 3.3673. Min Range: -3.3673

Max Act: 2.4814. Min Act: -0.0002

Data Index: 1135853 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 3.3673. Min Range: -3.3673

Max Act: 2.4845. Min Act: -0.0001

Data Index: 765940 (C4 (Web Text))

Max Activating Token Index: 972

Text #19

Max Range: 3.3673. Min Range: -3.3673

Max Act: 2.3448. Min Act: -0.0001

Data Index: 731382 (C4 (Web Text))

Max Activating Token Index: 814