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

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

Neuron 3249 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0086. Min Range: -1.0086

Max Act: 1.0086. Min Act: -0.0000

Data Index: 767098 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.9416. Min Act: -0.0000

Data Index: 191746 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.9711. Min Act: -0.0000

Data Index: 469123 (C4 (Web Text))

Max Activating Token Index: 955

Text #3

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.7543. Min Act: -0.0000

Data Index: 1237919 (C4 (Web Text))

Max Activating Token Index: 822

Text #4

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.7605. Min Act: -0.0000

Data Index: 865813 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.7837. Min Act: -0.0000

Data Index: 1218707 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.6790. Min Act: 0.0000

Data Index: 539320 (C4 (Web Text))

Max Activating Token Index: 711

Text #7

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.7109. Min Act: -0.0000

Data Index: 1258470 (C4 (Web Text))

Max Activating Token Index: 909

Text #8

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.7778. Min Act: -0.0000

Data Index: 788841 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.7301. Min Act: -0.0000

Data Index: 1056591 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.6638. Min Act: -0.0000

Data Index: 152931 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.7058. Min Act: -0.0000

Data Index: 1096508 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.7088. Min Act: -0.0000

Data Index: 158403 (C4 (Web Text))

Max Activating Token Index: 944

Text #13

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.7002. Min Act: -0.0000

Data Index: 347727 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.6946. Min Act: -0.0000

Data Index: 234333 (C4 (Web Text))

Max Activating Token Index: 927

Text #15

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.7098. Min Act: -0.0000

Data Index: 882914 (C4 (Web Text))

Max Activating Token Index: 41

Text #16

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.6578. Min Act: -0.0000

Data Index: 1097144 (C4 (Web Text))

Max Activating Token Index: 776

Text #17

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.6693. Min Act: -0.0000

Data Index: 1286728 (C4 (Web Text))

Max Activating Token Index: 358

Text #18

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.6499. Min Act: 0.0000

Data Index: 411721 (C4 (Web Text))

Max Activating Token Index: 440

Text #19

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.6512. Min Act: -0.0000

Data Index: 194146 (C4 (Web Text))

Max Activating Token Index: 889