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

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

Neuron 5586 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: 0.1168. Min Range: -0.1168

Max Act: 0.1168. Min Act: -0.0002

Data Index: 833243 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1066. Min Act: -0.0002

Data Index: 1074262 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1018. Min Act: -0.0002

Data Index: 252495 (C4 (Web Text))

Max Activating Token Index: 414

Text #3

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0954. Min Act: -0.0002

Data Index: 1243252 (C4 (Web Text))

Max Activating Token Index: 731

Text #4

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0934. Min Act: -0.0002

Data Index: 1239655 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0959. Min Act: -0.0002

Data Index: 1062405 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0936. Min Act: -0.0002

Data Index: 876106 (C4 (Web Text))

Max Activating Token Index: 767

Text #7

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0956. Min Act: -0.0002

Data Index: 300300 (C4 (Web Text))

Max Activating Token Index: 817

Text #8

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0927. Min Act: -0.0002

Data Index: 1216361 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0885. Min Act: -0.0002

Data Index: 651314 (C4 (Web Text))

Max Activating Token Index: 325

Text #10

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0891. Min Act: -0.0002

Data Index: 1138667 (C4 (Web Text))

Max Activating Token Index: 948

Text #11

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0862. Min Act: -0.0002

Data Index: 620523 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0857. Min Act: -0.0003

Data Index: 871995 (C4 (Web Text))

Max Activating Token Index: 905

Text #13

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0825. Min Act: -0.0002

Data Index: 414646 (C4 (Web Text))

Max Activating Token Index: 457

Text #14

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0849. Min Act: -0.0002

Data Index: 653729 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0817. Min Act: -0.0002

Data Index: 507156 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0823. Min Act: -0.0002

Data Index: 150160 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0817. Min Act: -0.0002

Data Index: 1345172 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0803. Min Act: -0.0002

Data Index: 1358670 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0800. Min Act: -0.0002

Data Index: 333300 (C4 (Web Text))

Max Activating Token Index: 639