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

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

Neuron 5354 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: 1.4655. Min Range: -1.4655

Max Act: 1.4655. Min Act: -0.0002

Data Index: 844529 (C4 (Web Text))

Max Activating Token Index: 280

Text #1

Max Range: 1.4655. Min Range: -1.4655

Max Act: 1.3179. Min Act: -0.0002

Data Index: 414630 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 1.4655. Min Range: -1.4655

Max Act: 1.3114. Min Act: -0.0002

Data Index: 359625 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 1.4655. Min Range: -1.4655

Max Act: 1.2918. Min Act: -0.0002

Data Index: 1031082 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 1.4655. Min Range: -1.4655

Max Act: 1.2675. Min Act: -0.0002

Data Index: 33635 (C4 (Web Text))

Max Activating Token Index: 901

Text #5

Max Range: 1.4655. Min Range: -1.4655

Max Act: 1.2863. Min Act: -0.0002

Data Index: 1272573 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 1.4655. Min Range: -1.4655

Max Act: 1.2892. Min Act: -0.0002

Data Index: 1168234 (C4 (Web Text))

Max Activating Token Index: 96

Text #7

Max Range: 1.4655. Min Range: -1.4655

Max Act: 1.2738. Min Act: -0.0002

Data Index: 629424 (C4 (Web Text))

Max Activating Token Index: 782

Text #8

Max Range: 1.4655. Min Range: -1.4655

Max Act: 1.2167. Min Act: -0.0002

Data Index: 452257 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 1.4655. Min Range: -1.4655

Max Act: 1.2220. Min Act: -0.0002

Data Index: 322797 (C4 (Web Text))

Max Activating Token Index: 360

Text #10

Max Range: 1.4655. Min Range: -1.4655

Max Act: 1.2115. Min Act: -0.0002

Data Index: 11734 (C4 (Web Text))

Max Activating Token Index: 682

Text #11

Max Range: 1.4655. Min Range: -1.4655

Max Act: 1.2129. Min Act: -0.0002

Data Index: 981896 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 1.4655. Min Range: -1.4655

Max Act: 1.1656. Min Act: -0.0002

Data Index: 685325 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 1.4655. Min Range: -1.4655

Max Act: 1.1888. Min Act: -0.0002

Data Index: 457454 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 1.4655. Min Range: -1.4655

Max Act: 1.1629. Min Act: -0.0002

Data Index: 555397 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 1.4655. Min Range: -1.4655

Max Act: 1.1840. Min Act: -0.0002

Data Index: 1200361 (C4 (Web Text))

Max Activating Token Index: 277

Text #16

Max Range: 1.4655. Min Range: -1.4655

Max Act: 1.1622. Min Act: -0.0002

Data Index: 149769 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 1.4655. Min Range: -1.4655

Max Act: 1.1061. Min Act: -0.0002

Data Index: 1121731 (C4 (Web Text))

Max Activating Token Index: 6

Text #18

Max Range: 1.4655. Min Range: -1.4655

Max Act: 1.1454. Min Act: -0.0002

Data Index: 809467 (C4 (Web Text))

Max Activating Token Index: 600

Text #19

Max Range: 1.4655. Min Range: -1.4655

Max Act: 1.1197. Min Act: -0.0002

Data Index: 1058698 (C4 (Web Text))

Max Activating Token Index: 786