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

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

Neuron 631 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: 2.1044. Min Range: -2.1044

Max Act: 2.1044. Min Act: -0.0003

Data Index: 20361 (C4 (Web Text))

Max Activating Token Index: 174

Text #1

Max Range: 2.1044. Min Range: -2.1044

Max Act: 1.9933. Min Act: -0.0002

Data Index: 278708 (C4 (Web Text))

Max Activating Token Index: 726

Text #2

Max Range: 2.1044. Min Range: -2.1044

Max Act: 1.8355. Min Act: -0.0002

Data Index: 804626 (C4 (Web Text))

Max Activating Token Index: 552

Text #3

Max Range: 2.1044. Min Range: -2.1044

Max Act: 1.8292. Min Act: -0.0002

Data Index: 843748 (C4 (Web Text))

Max Activating Token Index: 735

Text #4

Max Range: 2.1044. Min Range: -2.1044

Max Act: 1.7844. Min Act: -0.0002

Data Index: 1114619 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 2.1044. Min Range: -2.1044

Max Act: 1.6760. Min Act: -0.0002

Data Index: 1306775 (C4 (Web Text))

Max Activating Token Index: 811

Text #6

Max Range: 2.1044. Min Range: -2.1044

Max Act: 1.7196. Min Act: -0.0003

Data Index: 600464 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 2.1044. Min Range: -2.1044

Max Act: 1.7624. Min Act: -0.0002

Data Index: 188895 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 2.1044. Min Range: -2.1044

Max Act: 1.7114. Min Act: -0.0002

Data Index: 212052 (C4 (Web Text))

Max Activating Token Index: 512

Text #9

Max Range: 2.1044. Min Range: -2.1044

Max Act: 1.6994. Min Act: -0.0003

Data Index: 1314910 (C4 (Web Text))

Max Activating Token Index: 322

Text #10

Max Range: 2.1044. Min Range: -2.1044

Max Act: 1.6876. Min Act: -0.0002

Data Index: 1155565 (C4 (Web Text))

Max Activating Token Index: 257

Text #11

Max Range: 2.1044. Min Range: -2.1044

Max Act: 1.6962. Min Act: -0.0002

Data Index: 630594 (C4 (Web Text))

Max Activating Token Index: 626

Text #12

Max Range: 2.1044. Min Range: -2.1044

Max Act: 1.6444. Min Act: -0.0002

Data Index: 1240182 (C4 (Web Text))

Max Activating Token Index: 246

Text #13

Max Range: 2.1044. Min Range: -2.1044

Max Act: 1.6913. Min Act: -0.0003

Data Index: 803386 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 2.1044. Min Range: -2.1044

Max Act: 1.6468. Min Act: -0.0003

Data Index: 98071 (C4 (Web Text))

Max Activating Token Index: 229

Text #15

Max Range: 2.1044. Min Range: -2.1044

Max Act: 1.6072. Min Act: -0.0002

Data Index: 934713 (C4 (Web Text))

Max Activating Token Index: 989

Text #16

Max Range: 2.1044. Min Range: -2.1044

Max Act: 1.6190. Min Act: -0.0002

Data Index: 606261 (C4 (Web Text))

Max Activating Token Index: 324

Text #17

Max Range: 2.1044. Min Range: -2.1044

Max Act: 1.5478. Min Act: -0.0002

Data Index: 1276794 (C4 (Web Text))

Max Activating Token Index: 613

Text #18

Max Range: 2.1044. Min Range: -2.1044

Max Act: 1.6305. Min Act: -0.0002

Data Index: 819410 (C4 (Web Text))

Max Activating Token Index: 542

Text #19

Max Range: 2.1044. Min Range: -2.1044

Max Act: 1.6136. Min Act: -0.0003

Data Index: 1039164 (C4 (Web Text))

Max Activating Token Index: 622