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

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

Neuron 960 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: 1.2138. Min Range: -1.2138

Max Act: 1.2138. Min Act: -0.0000

Data Index: 558066 (C4 (Web Text))

Max Activating Token Index: 504

Text #1

Max Range: 1.2138. Min Range: -1.2138

Max Act: 1.0953. Min Act: -0.0000

Data Index: 792079 (C4 (Web Text))

Max Activating Token Index: 491

Text #2

Max Range: 1.2138. Min Range: -1.2138

Max Act: 1.0506. Min Act: -0.0000

Data Index: 1231594 (C4 (Web Text))

Max Activating Token Index: 577

Text #3

Max Range: 1.2138. Min Range: -1.2138

Max Act: 1.0843. Min Act: -0.0000

Data Index: 501811 (C4 (Web Text))

Max Activating Token Index: 490

Text #4

Max Range: 1.2138. Min Range: -1.2138

Max Act: 0.9941. Min Act: 0.0000

Data Index: 103089 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 1.2138. Min Range: -1.2138

Max Act: 1.0139. Min Act: -0.0000

Data Index: 625097 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 1.2138. Min Range: -1.2138

Max Act: 0.9939. Min Act: -0.0000

Data Index: 156885 (C4 (Web Text))

Max Activating Token Index: 746

Text #7

Max Range: 1.2138. Min Range: -1.2138

Max Act: 1.0159. Min Act: -0.0000

Data Index: 570927 (C4 (Web Text))

Max Activating Token Index: 571

Text #8

Max Range: 1.2138. Min Range: -1.2138

Max Act: 0.9836. Min Act: -0.0000

Data Index: 243342 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 1.2138. Min Range: -1.2138

Max Act: 0.9416. Min Act: -0.0000

Data Index: 590727 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 1.2138. Min Range: -1.2138

Max Act: 1.0238. Min Act: -0.0000

Data Index: 1212082 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 1.2138. Min Range: -1.2138

Max Act: 0.9084. Min Act: 0.0000

Data Index: 754179 (C4 (Web Text))

Max Activating Token Index: 783

Text #12

Max Range: 1.2138. Min Range: -1.2138

Max Act: 0.9302. Min Act: -0.0000

Data Index: 318505 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 1.2138. Min Range: -1.2138

Max Act: 0.8992. Min Act: -0.0000

Data Index: 615695 (C4 (Web Text))

Max Activating Token Index: 905

Text #14

Max Range: 1.2138. Min Range: -1.2138

Max Act: 0.9259. Min Act: -0.0000

Data Index: 1027807 (C4 (Web Text))

Max Activating Token Index: 944

Text #15

Max Range: 1.2138. Min Range: -1.2138

Max Act: 0.7884. Min Act: 0.0000

Data Index: 492656 (C4 (Web Text))

Max Activating Token Index: 146

Text #16

Max Range: 1.2138. Min Range: -1.2138

Max Act: 0.9179. Min Act: 0.0001

Data Index: 727475 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 1.2138. Min Range: -1.2138

Max Act: 0.9134. Min Act: -0.0000

Data Index: 1647691 (Python Code)

Max Activating Token Index: 428

Text #18

Max Range: 1.2138. Min Range: -1.2138

Max Act: 0.9349. Min Act: -0.0000

Data Index: 1056492 (C4 (Web Text))

Max Activating Token Index: 792

Text #19

Max Range: 1.2138. Min Range: -1.2138

Max Act: 0.9020. Min Act: 0.0000

Data Index: 205400 (C4 (Web Text))

Max Activating Token Index: 968