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

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

Neuron 6077 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: 1.0110. Min Range: -1.0110

Max Act: 1.0110. Min Act: -0.0002

Data Index: 201034 (C4 (Web Text))

Max Activating Token Index: 466

Text #1

Max Range: 1.0110. Min Range: -1.0110

Max Act: 1.0085. Min Act: -0.0002

Data Index: 492432 (C4 (Web Text))

Max Activating Token Index: 791

Text #2

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.9849. Min Act: -0.0002

Data Index: 386076 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.9607. Min Act: -0.0002

Data Index: 1199432 (C4 (Web Text))

Max Activating Token Index: 897

Text #4

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.9511. Min Act: -0.0002

Data Index: 1068787 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.9338. Min Act: -0.0002

Data Index: 1004964 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.9219. Min Act: -0.0002

Data Index: 1239947 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.9420. Min Act: -0.0002

Data Index: 1273630 (C4 (Web Text))

Max Activating Token Index: 579

Text #8

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.9332. Min Act: -0.0002

Data Index: 718258 (C4 (Web Text))

Max Activating Token Index: 865

Text #9

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.9117. Min Act: -0.0002

Data Index: 1063775 (C4 (Web Text))

Max Activating Token Index: 914

Text #10

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.9031. Min Act: -0.0002

Data Index: 516129 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.9142. Min Act: -0.0002

Data Index: 826627 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.9228. Min Act: -0.0002

Data Index: 825409 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.8919. Min Act: -0.0002

Data Index: 272180 (C4 (Web Text))

Max Activating Token Index: 1017

Text #14

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.8862. Min Act: -0.0002

Data Index: 975610 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.8936. Min Act: -0.0003

Data Index: 1100704 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.8892. Min Act: -0.0002

Data Index: 468368 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.8944. Min Act: -0.0002

Data Index: 164723 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.8867. Min Act: -0.0002

Data Index: 564467 (C4 (Web Text))

Max Activating Token Index: 578

Text #19

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.8783. Min Act: -0.0002

Data Index: 418559 (C4 (Web Text))

Max Activating Token Index: 175