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

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

Neuron 4881 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.1044. Min Act: -0.0002

Data Index: 1236007 (C4 (Web Text))

Max Activating Token Index: 835

Text #1

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0982. Min Act: -0.0002

Data Index: 1237550 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.1054. Min Act: -0.0002

Data Index: 189856 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0879. Min Act: -0.0002

Data Index: 595082 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0884. Min Act: -0.0002

Data Index: 605081 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0996. Min Act: -0.0002

Data Index: 1162205 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0943. Min Act: -0.0002

Data Index: 481553 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.1086. Min Act: -0.0002

Data Index: 51667 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0956. Min Act: -0.0002

Data Index: 474940 (C4 (Web Text))

Max Activating Token Index: 134

Text #9

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0903. Min Act: -0.0002

Data Index: 578044 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0910. Min Act: -0.0002

Data Index: 275080 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0979. Min Act: -0.0002

Data Index: 1080706 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0923. Min Act: -0.0002

Data Index: 960220 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0814. Min Act: -0.0002

Data Index: 351936 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0796. Min Act: -0.0002

Data Index: 930066 (C4 (Web Text))

Max Activating Token Index: 939

Text #15

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0845. Min Act: -0.0002

Data Index: 1297086 (C4 (Web Text))

Max Activating Token Index: 129

Text #16

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0923. Min Act: -0.0002

Data Index: 442724 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0896. Min Act: -0.0002

Data Index: 971812 (C4 (Web Text))

Max Activating Token Index: 3

Text #18

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0948. Min Act: -0.0002

Data Index: 312566 (C4 (Web Text))

Max Activating Token Index: 916

Text #19

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0886. Min Act: -0.0002

Data Index: 206152 (C4 (Web Text))

Max Activating Token Index: 15