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

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

Neuron 5352 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: 1.8865. Min Range: -1.8865

Max Act: 1.8865. Min Act: -0.0003

Data Index: 892403 (C4 (Web Text))

Max Activating Token Index: 738

Text #1

Max Range: 1.8865. Min Range: -1.8865

Max Act: 1.7901. Min Act: -0.0002

Data Index: 247628 (C4 (Web Text))

Max Activating Token Index: 383

Text #2

Max Range: 1.8865. Min Range: -1.8865

Max Act: 1.7935. Min Act: -0.0002

Data Index: 997374 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 1.8865. Min Range: -1.8865

Max Act: 1.7374. Min Act: -0.0002

Data Index: 683926 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 1.8865. Min Range: -1.8865

Max Act: 1.7049. Min Act: -0.0002

Data Index: 600602 (C4 (Web Text))

Max Activating Token Index: 890

Text #5

Max Range: 1.8865. Min Range: -1.8865

Max Act: 1.6885. Min Act: -0.0003

Data Index: 985187 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 1.8865. Min Range: -1.8865

Max Act: 1.6664. Min Act: -0.0002

Data Index: 953290 (C4 (Web Text))

Max Activating Token Index: 909

Text #7

Max Range: 1.8865. Min Range: -1.8865

Max Act: 1.6590. Min Act: -0.0002

Data Index: 624969 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 1.8865. Min Range: -1.8865

Max Act: 1.6560. Min Act: -0.0002

Data Index: 1210483 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 1.8865. Min Range: -1.8865

Max Act: 1.6430. Min Act: -0.0002

Data Index: 636328 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 1.8865. Min Range: -1.8865

Max Act: 1.6603. Min Act: -0.0002

Data Index: 163693 (C4 (Web Text))

Max Activating Token Index: 3

Text #11

Max Range: 1.8865. Min Range: -1.8865

Max Act: 1.6582. Min Act: -0.0002

Data Index: 548629 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 1.8865. Min Range: -1.8865

Max Act: 1.6330. Min Act: -0.0002

Data Index: 31524 (C4 (Web Text))

Max Activating Token Index: 554

Text #13

Max Range: 1.8865. Min Range: -1.8865

Max Act: 1.6013. Min Act: -0.0002

Data Index: 1278090 (C4 (Web Text))

Max Activating Token Index: 5

Text #14

Max Range: 1.8865. Min Range: -1.8865

Max Act: 1.6416. Min Act: -0.0002

Data Index: 1343098 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 1.8865. Min Range: -1.8865

Max Act: 1.5950. Min Act: -0.0002

Data Index: 1104923 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 1.8865. Min Range: -1.8865

Max Act: 1.6425. Min Act: -0.0002

Data Index: 893669 (C4 (Web Text))

Max Activating Token Index: 300

Text #17

Max Range: 1.8865. Min Range: -1.8865

Max Act: 1.5639. Min Act: -0.0002

Data Index: 896115 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 1.8865. Min Range: -1.8865

Max Act: 1.6193. Min Act: -0.0002

Data Index: 168798 (C4 (Web Text))

Max Activating Token Index: 821

Text #19

Max Range: 1.8865. Min Range: -1.8865

Max Act: 1.5741. Min Act: -0.0002

Data Index: 223181 (C4 (Web Text))

Max Activating Token Index: 341