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

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

Neuron 1401 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: 3.3741. Min Range: -3.3741

Max Act: 3.3741. Min Act: -0.0002

Data Index: 768283 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 3.3741. Min Range: -3.3741

Max Act: 3.1851. Min Act: -0.0002

Data Index: 587031 (C4 (Web Text))

Max Activating Token Index: 814

Text #2

Max Range: 3.3741. Min Range: -3.3741

Max Act: 3.1119. Min Act: -0.0002

Data Index: 594348 (C4 (Web Text))

Max Activating Token Index: 841

Text #3

Max Range: 3.3741. Min Range: -3.3741

Max Act: 3.0650. Min Act: -0.0002

Data Index: 10519 (C4 (Web Text))

Max Activating Token Index: 672

Text #4

Max Range: 3.3741. Min Range: -3.3741

Max Act: 3.0456. Min Act: -0.0002

Data Index: 102594 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 3.3741. Min Range: -3.3741

Max Act: 3.0401. Min Act: -0.0002

Data Index: 887965 (C4 (Web Text))

Max Activating Token Index: 118

Text #6

Max Range: 3.3741. Min Range: -3.3741

Max Act: 2.9899. Min Act: -0.0002

Data Index: 514924 (C4 (Web Text))

Max Activating Token Index: 281

Text #7

Max Range: 3.3741. Min Range: -3.3741

Max Act: 2.9855. Min Act: -0.0002

Data Index: 1227512 (C4 (Web Text))

Max Activating Token Index: 394

Text #8

Max Range: 3.3741. Min Range: -3.3741

Max Act: 2.9753. Min Act: -0.0002

Data Index: 1252709 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 3.3741. Min Range: -3.3741

Max Act: 2.9348. Min Act: -0.0002

Data Index: 902934 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 3.3741. Min Range: -3.3741

Max Act: 2.9789. Min Act: -0.0002

Data Index: 539339 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 3.3741. Min Range: -3.3741

Max Act: 2.8958. Min Act: -0.0002

Data Index: 103604 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 3.3741. Min Range: -3.3741

Max Act: 2.8067. Min Act: -0.0002

Data Index: 716748 (C4 (Web Text))

Max Activating Token Index: 302

Text #13

Max Range: 3.3741. Min Range: -3.3741

Max Act: 2.8069. Min Act: -0.0003

Data Index: 664185 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 3.3741. Min Range: -3.3741

Max Act: 2.8627. Min Act: -0.0002

Data Index: 889261 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 3.3741. Min Range: -3.3741

Max Act: 2.8905. Min Act: -0.0002

Data Index: 856883 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 3.3741. Min Range: -3.3741

Max Act: 2.8238. Min Act: -0.0002

Data Index: 767166 (C4 (Web Text))

Max Activating Token Index: 88

Text #17

Max Range: 3.3741. Min Range: -3.3741

Max Act: 2.8876. Min Act: -0.0002

Data Index: 423141 (C4 (Web Text))

Max Activating Token Index: 401

Text #18

Max Range: 3.3741. Min Range: -3.3741

Max Act: 2.8222. Min Act: -0.0003

Data Index: 1345520 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 3.3741. Min Range: -3.3741

Max Act: 2.7955. Min Act: -0.0002

Data Index: 937911 (C4 (Web Text))

Max Activating Token Index: 204