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

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

Neuron 4337 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: 2.9629. Min Range: -2.9629

Max Act: 2.9629. Min Act: -0.0002

Data Index: 1059404 (C4 (Web Text))

Max Activating Token Index: 314

Text #1

Max Range: 2.9629. Min Range: -2.9629

Max Act: 2.8784. Min Act: -0.0002

Data Index: 594872 (C4 (Web Text))

Max Activating Token Index: 565

Text #2

Max Range: 2.9629. Min Range: -2.9629

Max Act: 2.7634. Min Act: -0.0002

Data Index: 644736 (C4 (Web Text))

Max Activating Token Index: 99

Text #3

Max Range: 2.9629. Min Range: -2.9629

Max Act: 2.7581. Min Act: -0.0002

Data Index: 894799 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 2.9629. Min Range: -2.9629

Max Act: 2.6688. Min Act: -0.0002

Data Index: 551796 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 2.9629. Min Range: -2.9629

Max Act: 2.6267. Min Act: -0.0003

Data Index: 1201020 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 2.9629. Min Range: -2.9629

Max Act: 2.7177. Min Act: -0.0002

Data Index: 161695 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 2.9629. Min Range: -2.9629

Max Act: 2.5679. Min Act: -0.0002

Data Index: 1066263 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 2.9629. Min Range: -2.9629

Max Act: 2.6588. Min Act: -0.0002

Data Index: 247475 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 2.9629. Min Range: -2.9629

Max Act: 2.5316. Min Act: -0.0003

Data Index: 1312546 (C4 (Web Text))

Max Activating Token Index: 484

Text #10

Max Range: 2.9629. Min Range: -2.9629

Max Act: 2.5801. Min Act: -0.0002

Data Index: 88671 (C4 (Web Text))

Max Activating Token Index: 452

Text #11

Max Range: 2.9629. Min Range: -2.9629

Max Act: 2.5120. Min Act: -0.0002

Data Index: 937765 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 2.9629. Min Range: -2.9629

Max Act: 2.5531. Min Act: -0.0002

Data Index: 838640 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 2.9629. Min Range: -2.9629

Max Act: 2.5671. Min Act: -0.0002

Data Index: 517322 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 2.9629. Min Range: -2.9629

Max Act: 2.4743. Min Act: -0.0002

Data Index: 605411 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 2.9629. Min Range: -2.9629

Max Act: 2.4886. Min Act: -0.0002

Data Index: 1174516 (C4 (Web Text))

Max Activating Token Index: 522

Text #16

Max Range: 2.9629. Min Range: -2.9629

Max Act: 2.4683. Min Act: -0.0002

Data Index: 433102 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 2.9629. Min Range: -2.9629

Max Act: 2.4511. Min Act: -0.0003

Data Index: 952761 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 2.9629. Min Range: -2.9629

Max Act: 2.4553. Min Act: -0.0002

Data Index: 902028 (C4 (Web Text))

Max Activating Token Index: 401

Text #19

Max Range: 2.9629. Min Range: -2.9629

Max Act: 2.4457. Min Act: -0.0002

Data Index: 791106 (C4 (Web Text))

Max Activating Token Index: 237