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

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

Neuron 2792 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.5086. Min Act: -0.0001

Data Index: 431381 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.4205. Min Act: -0.0001

Data Index: 384840 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.4102. Min Act: -0.0001

Data Index: 513999 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.4023. Min Act: -0.0001

Data Index: 655494 (C4 (Web Text))

Max Activating Token Index: 713

Text #4

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.3927. Min Act: -0.0001

Data Index: 979913 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.3902. Min Act: -0.0001

Data Index: 412274 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.3965. Min Act: -0.0001

Data Index: 523220 (C4 (Web Text))

Max Activating Token Index: 401

Text #7

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.4339. Min Act: -0.0001

Data Index: 886517 (C4 (Web Text))

Max Activating Token Index: 383

Text #8

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.3945. Min Act: -0.0001

Data Index: 412801 (C4 (Web Text))

Max Activating Token Index: 568

Text #9

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.4008. Min Act: -0.0001

Data Index: 1156923 (C4 (Web Text))

Max Activating Token Index: 238

Text #10

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.3996. Min Act: -0.0001

Data Index: 846054 (C4 (Web Text))

Max Activating Token Index: 816

Text #11

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.4113. Min Act: -0.0001

Data Index: 415688 (C4 (Web Text))

Max Activating Token Index: 308

Text #12

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.3979. Min Act: -0.0001

Data Index: 747314 (C4 (Web Text))

Max Activating Token Index: 757

Text #13

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.3842. Min Act: -0.0001

Data Index: 845876 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.4090. Min Act: -0.0001

Data Index: 75676 (C4 (Web Text))

Max Activating Token Index: 281

Text #15

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.4048. Min Act: -0.0001

Data Index: 571706 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.3675. Min Act: -0.0001

Data Index: 560553 (C4 (Web Text))

Max Activating Token Index: 223

Text #17

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.3608. Min Act: -0.0001

Data Index: 67928 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.3771. Min Act: -0.0001

Data Index: 1019529 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.3784. Min Act: -0.0001

Data Index: 528068 (C4 (Web Text))

Max Activating Token Index: 466