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

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

Neuron 4545 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: 0.0874. Min Range: -0.0874

Max Act: 0.0873. Min Act: -0.0002

Data Index: 1315630 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0855. Min Act: -0.0002

Data Index: 1046392 (C4 (Web Text))

Max Activating Token Index: 587

Text #2

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0843. Min Act: -0.0002

Data Index: 1131266 (C4 (Web Text))

Max Activating Token Index: 770

Text #3

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0857. Min Act: -0.0002

Data Index: 1148341 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0874. Min Act: -0.0002

Data Index: 885697 (C4 (Web Text))

Max Activating Token Index: 828

Text #5

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0841. Min Act: -0.0002

Data Index: 943773 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0819. Min Act: -0.0002

Data Index: 956548 (C4 (Web Text))

Max Activating Token Index: 514

Text #7

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0814. Min Act: -0.0002

Data Index: 985040 (C4 (Web Text))

Max Activating Token Index: 991

Text #8

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0817. Min Act: -0.0002

Data Index: 47923 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0826. Min Act: -0.0003

Data Index: 203255 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0822. Min Act: -0.0002

Data Index: 625740 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0821. Min Act: -0.0002

Data Index: 193703 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0809. Min Act: -0.0002

Data Index: 320731 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0814. Min Act: -0.0002

Data Index: 1284301 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0800. Min Act: -0.0002

Data Index: 1115340 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0815. Min Act: -0.0002

Data Index: 201923 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0790. Min Act: -0.0002

Data Index: 1309233 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0792. Min Act: -0.0002

Data Index: 605846 (C4 (Web Text))

Max Activating Token Index: 223

Text #18

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0790. Min Act: -0.0002

Data Index: 487905 (C4 (Web Text))

Max Activating Token Index: 442

Text #19

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0790. Min Act: -0.0002

Data Index: 284477 (C4 (Web Text))

Max Activating Token Index: 478