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

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

Neuron 3405 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.1002. Min Act: -0.0002

Data Index: 85860 (C4 (Web Text))

Max Activating Token Index: 483

Text #1

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0974. Min Act: -0.0002

Data Index: 203872 (C4 (Web Text))

Max Activating Token Index: 542

Text #2

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0960. Min Act: -0.0002

Data Index: 1051021 (C4 (Web Text))

Max Activating Token Index: 443

Text #3

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0955. Min Act: -0.0002

Data Index: 539850 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0950. Min Act: -0.0002

Data Index: 71149 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0932. Min Act: -0.0002

Data Index: 467788 (C4 (Web Text))

Max Activating Token Index: 695

Text #6

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0931. Min Act: -0.0002

Data Index: 419513 (C4 (Web Text))

Max Activating Token Index: 62

Text #7

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0935. Min Act: -0.0002

Data Index: 523639 (C4 (Web Text))

Max Activating Token Index: 323

Text #8

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0909. Min Act: -0.0002

Data Index: 791451 (C4 (Web Text))

Max Activating Token Index: 538

Text #9

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0909. Min Act: -0.0002

Data Index: 182161 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0913. Min Act: -0.0002

Data Index: 825973 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0916. Min Act: -0.0002

Data Index: 1213645 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0893. Min Act: -0.0002

Data Index: 825011 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0886. Min Act: -0.0002

Data Index: 486447 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0871. Min Act: -0.0002

Data Index: 1210419 (C4 (Web Text))

Max Activating Token Index: 281

Text #15

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0869. Min Act: -0.0002

Data Index: 1108639 (C4 (Web Text))

Max Activating Token Index: 485

Text #16

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0874. Min Act: -0.0002

Data Index: 1229272 (C4 (Web Text))

Max Activating Token Index: 915

Text #17

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0869. Min Act: -0.0002

Data Index: 443985 (C4 (Web Text))

Max Activating Token Index: 866

Text #18

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0870. Min Act: -0.0002

Data Index: 636052 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0865. Min Act: -0.0002

Data Index: 757498 (C4 (Web Text))

Max Activating Token Index: 699