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

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

Neuron 74 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: 0.1253. Min Range: -0.1253

Max Act: 0.1253. Min Act: -0.0001

Data Index: 261041 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1144. Min Act: -0.0001

Data Index: 16009 (C4 (Web Text))

Max Activating Token Index: 428

Text #2

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1050. Min Act: -0.0002

Data Index: 68772 (C4 (Web Text))

Max Activating Token Index: 903

Text #3

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1040. Min Act: -0.0001

Data Index: 86039 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1048. Min Act: -0.0002

Data Index: 1296603 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1049. Min Act: -0.0002

Data Index: 861651 (C4 (Web Text))

Max Activating Token Index: 784

Text #6

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1041. Min Act: -0.0001

Data Index: 994950 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1010. Min Act: -0.0001

Data Index: 329313 (C4 (Web Text))

Max Activating Token Index: 873

Text #8

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0973. Min Act: -0.0002

Data Index: 426539 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0881. Min Act: -0.0002

Data Index: 1164645 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0894. Min Act: -0.0002

Data Index: 857911 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0840. Min Act: -0.0001

Data Index: 695336 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0816. Min Act: -0.0001

Data Index: 1012837 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0857. Min Act: -0.0002

Data Index: 1070936 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0921. Min Act: -0.0002

Data Index: 613109 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0845. Min Act: -0.0002

Data Index: 238729 (C4 (Web Text))

Max Activating Token Index: 946

Text #16

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0851. Min Act: -0.0001

Data Index: 288260 (C4 (Web Text))

Max Activating Token Index: 315

Text #17

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0788. Min Act: -0.0002

Data Index: 1347066 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0860. Min Act: -0.0001

Data Index: 1207419 (C4 (Web Text))

Max Activating Token Index: 681

Text #19

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0789. Min Act: -0.0002

Data Index: 950793 (C4 (Web Text))

Max Activating Token Index: 836