Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1546 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2908. Min Act: -0.0000

Data Index: 830512 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2441. Min Act: 0.0000

Data Index: 25797 (C4 (Web Text))

Max Activating Token Index: 927

Text #2

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2312. Min Act: 0.0000

Data Index: 298378 (C4 (Web Text))

Max Activating Token Index: 557

Text #3

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2323. Min Act: 0.0000

Data Index: 867157 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2148. Min Act: -0.0000

Data Index: 490445 (C4 (Web Text))

Max Activating Token Index: 955

Text #5

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2318. Min Act: -0.0000

Data Index: 908443 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2082. Min Act: 0.0000

Data Index: 937896 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2248. Min Act: 0.0001

Data Index: 746924 (C4 (Web Text))

Max Activating Token Index: 916

Text #8

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2208. Min Act: 0.0002

Data Index: 797958 (C4 (Web Text))

Max Activating Token Index: 188

Text #9

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2157. Min Act: -0.0000

Data Index: 789966 (C4 (Web Text))

Max Activating Token Index: 178

Text #10

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2090. Min Act: -0.0001

Data Index: 1020936 (C4 (Web Text))

Max Activating Token Index: 130

Text #11

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.1989. Min Act: 0.0000

Data Index: 935117 (C4 (Web Text))

Max Activating Token Index: 337

Text #12

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.1950. Min Act: -0.0001

Data Index: 1310707 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2015. Min Act: 0.0002

Data Index: 293024 (C4 (Web Text))

Max Activating Token Index: 9

Text #14

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2003. Min Act: 0.0003

Data Index: 510544 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2002. Min Act: -0.0000

Data Index: 764343 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.1970. Min Act: -0.0000

Data Index: 117782 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.1953. Min Act: 0.0000

Data Index: 57656 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.1891. Min Act: -0.0000

Data Index: 905662 (C4 (Web Text))

Max Activating Token Index: 219

Text #19

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.1952. Min Act: 0.0001

Data Index: 882876 (C4 (Web Text))

Max Activating Token Index: 943