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

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

Neuron 143 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.4737. Min Act: -0.0000

Data Index: 137288 (C4 (Web Text))

Max Activating Token Index: 610

Text #1

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.4249. Min Act: -0.0000

Data Index: 934113 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.4041. Min Act: -0.0000

Data Index: 1296254 (C4 (Web Text))

Max Activating Token Index: 625

Text #3

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.4008. Min Act: -0.0000

Data Index: 999974 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.3571. Min Act: -0.0000

Data Index: 721272 (C4 (Web Text))

Max Activating Token Index: 507

Text #5

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.3520. Min Act: -0.0000

Data Index: 1065722 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.3633. Min Act: -0.0000

Data Index: 1349467 (C4 (Web Text))

Max Activating Token Index: 775

Text #7

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.3131. Min Act: -0.0000

Data Index: 936483 (C4 (Web Text))

Max Activating Token Index: 777

Text #8

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.3270. Min Act: -0.0000

Data Index: 816217 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.2987. Min Act: -0.0000

Data Index: 558014 (C4 (Web Text))

Max Activating Token Index: 486

Text #10

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.3372. Min Act: -0.0000

Data Index: 481259 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.3109. Min Act: -0.0000

Data Index: 9516 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.3107. Min Act: -0.0000

Data Index: 449281 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.3042. Min Act: -0.0000

Data Index: 178530 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.2900. Min Act: -0.0000

Data Index: 664672 (C4 (Web Text))

Max Activating Token Index: 454

Text #15

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.3002. Min Act: -0.0000

Data Index: 510847 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.3084. Min Act: -0.0000

Data Index: 673244 (C4 (Web Text))

Max Activating Token Index: 321

Text #17

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.3145. Min Act: -0.0000

Data Index: 634569 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.2882. Min Act: -0.0000

Data Index: 883354 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.2784. Min Act: -0.0000

Data Index: 1331132 (C4 (Web Text))

Max Activating Token Index: 826