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

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

Neuron 3763 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8146. Min Range: -3.8146

Max Act: 3.8146. Min Act: -0.0001

Data Index: 681177 (C4 (Web Text))

Max Activating Token Index: 797

Text #1

Max Range: 3.8146. Min Range: -3.8146

Max Act: 3.3587. Min Act: -0.0000

Data Index: 217654 (C4 (Web Text))

Max Activating Token Index: 526

Text #2

Max Range: 3.8146. Min Range: -3.8146

Max Act: 3.4935. Min Act: -0.0001

Data Index: 565722 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 3.8146. Min Range: -3.8146

Max Act: 3.4005. Min Act: -0.0001

Data Index: 1046516 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 3.8146. Min Range: -3.8146

Max Act: 3.3679. Min Act: -0.0001

Data Index: 1094906 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 3.8146. Min Range: -3.8146

Max Act: 3.3074. Min Act: -0.0001

Data Index: 907933 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 3.8146. Min Range: -3.8146

Max Act: 3.1800. Min Act: -0.0000

Data Index: 49674 (C4 (Web Text))

Max Activating Token Index: 749

Text #7

Max Range: 3.8146. Min Range: -3.8146

Max Act: 3.3247. Min Act: -0.0001

Data Index: 656709 (C4 (Web Text))

Max Activating Token Index: 475

Text #8

Max Range: 3.8146. Min Range: -3.8146

Max Act: 2.7830. Min Act: -0.0000

Data Index: 549619 (C4 (Web Text))

Max Activating Token Index: 247

Text #9

Max Range: 3.8146. Min Range: -3.8146

Max Act: 2.8971. Min Act: -0.0000

Data Index: 1132598 (C4 (Web Text))

Max Activating Token Index: 1022

Text #10

Max Range: 3.8146. Min Range: -3.8146

Max Act: 2.6564. Min Act: -0.0001

Data Index: 730905 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 3.8146. Min Range: -3.8146

Max Act: 2.6426. Min Act: -0.0001

Data Index: 546658 (C4 (Web Text))

Max Activating Token Index: 1013

Text #12

Max Range: 3.8146. Min Range: -3.8146

Max Act: 2.4558. Min Act: -0.0000

Data Index: 20223 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 3.8146. Min Range: -3.8146

Max Act: 2.8795. Min Act: -0.0001

Data Index: 927151 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 3.8146. Min Range: -3.8146

Max Act: 2.4889. Min Act: -0.0001

Data Index: 991369 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 3.8146. Min Range: -3.8146

Max Act: 2.3171. Min Act: -0.0000

Data Index: 1238185 (C4 (Web Text))

Max Activating Token Index: 752

Text #16

Max Range: 3.8146. Min Range: -3.8146

Max Act: 2.6054. Min Act: -0.0000

Data Index: 692009 (C4 (Web Text))

Max Activating Token Index: 324

Text #17

Max Range: 3.8146. Min Range: -3.8146

Max Act: 2.5701. Min Act: -0.0000

Data Index: 505264 (C4 (Web Text))

Max Activating Token Index: 809

Text #18

Max Range: 3.8146. Min Range: -3.8146

Max Act: 2.4244. Min Act: -0.0000

Data Index: 721929 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 3.8146. Min Range: -3.8146

Max Act: 2.5711. Min Act: -0.0000

Data Index: 99388 (C4 (Web Text))

Max Activating Token Index: 860