Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2421 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.4563. Min Range: -2.4563

Max Act: 2.4563. Min Act: -0.0000

Data Index: 970004 (C4 (Web Text))

Max Activating Token Index: 335

Text #1

Max Range: 2.4563. Min Range: -2.4563

Max Act: 2.1134. Min Act: -0.0000

Data Index: 752976 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 2.4563. Min Range: -2.4563

Max Act: 2.0153. Min Act: -0.0000

Data Index: 694526 (C4 (Web Text))

Max Activating Token Index: 77

Text #3

Max Range: 2.4563. Min Range: -2.4563

Max Act: 1.8996. Min Act: -0.0000

Data Index: 456333 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 2.4563. Min Range: -2.4563

Max Act: 1.7854. Min Act: -0.0000

Data Index: 1022799 (C4 (Web Text))

Max Activating Token Index: 127

Text #5

Max Range: 2.4563. Min Range: -2.4563

Max Act: 1.8755. Min Act: -0.0000

Data Index: 1256950 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 2.4563. Min Range: -2.4563

Max Act: 1.7949. Min Act: -0.0000

Data Index: 1250154 (C4 (Web Text))

Max Activating Token Index: 839

Text #7

Max Range: 2.4563. Min Range: -2.4563

Max Act: 1.7761. Min Act: -0.0000

Data Index: 1298758 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 2.4563. Min Range: -2.4563

Max Act: 1.7297. Min Act: -0.0000

Data Index: 1201793 (C4 (Web Text))

Max Activating Token Index: 170

Text #9

Max Range: 2.4563. Min Range: -2.4563

Max Act: 1.6594. Min Act: -0.0000

Data Index: 1267302 (C4 (Web Text))

Max Activating Token Index: 324

Text #10

Max Range: 2.4563. Min Range: -2.4563

Max Act: 1.5722. Min Act: -0.0000

Data Index: 134507 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 2.4563. Min Range: -2.4563

Max Act: 1.7535. Min Act: -0.0000

Data Index: 1337602 (C4 (Web Text))

Max Activating Token Index: 694

Text #12

Max Range: 2.4563. Min Range: -2.4563

Max Act: 1.5376. Min Act: 0.0000

Data Index: 1337083 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 2.4563. Min Range: -2.4563

Max Act: 1.5603. Min Act: -0.0000

Data Index: 615828 (C4 (Web Text))

Max Activating Token Index: 491

Text #14

Max Range: 2.4563. Min Range: -2.4563

Max Act: 1.4818. Min Act: -0.0000

Data Index: 858131 (C4 (Web Text))

Max Activating Token Index: 729

Text #15

Max Range: 2.4563. Min Range: -2.4563

Max Act: 1.4054. Min Act: -0.0000

Data Index: 171479 (C4 (Web Text))

Max Activating Token Index: 184

Text #16

Max Range: 2.4563. Min Range: -2.4563

Max Act: 1.4104. Min Act: -0.0000

Data Index: 410931 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 2.4563. Min Range: -2.4563

Max Act: 1.4213. Min Act: -0.0000

Data Index: 47873 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 2.4563. Min Range: -2.4563

Max Act: 1.2972. Min Act: -0.0000

Data Index: 60180 (C4 (Web Text))

Max Activating Token Index: 146

Text #19

Max Range: 2.4563. Min Range: -2.4563

Max Act: 1.4441. Min Act: -0.0000

Data Index: 789750 (C4 (Web Text))

Max Activating Token Index: 753