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

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

Neuron 1784 in Layer 0

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: 0.4160. Min Range: -0.4160

Max Act: 0.4160. Min Act: -0.0001

Data Index: 1125475 (C4 (Web Text))

Max Activating Token Index: 107

Text #1

Max Range: 0.4160. Min Range: -0.4160

Max Act: 0.3846. Min Act: -0.0001

Data Index: 207163 (C4 (Web Text))

Max Activating Token Index: 720

Text #2

Max Range: 0.4160. Min Range: -0.4160

Max Act: 0.3808. Min Act: -0.0001

Data Index: 534880 (C4 (Web Text))

Max Activating Token Index: 309

Text #3

Max Range: 0.4160. Min Range: -0.4160

Max Act: 0.3772. Min Act: -0.0001

Data Index: 966081 (C4 (Web Text))

Max Activating Token Index: 579

Text #4

Max Range: 0.4160. Min Range: -0.4160

Max Act: 0.3730. Min Act: -0.0001

Data Index: 70396 (C4 (Web Text))

Max Activating Token Index: 444

Text #5

Max Range: 0.4160. Min Range: -0.4160

Max Act: 0.3777. Min Act: -0.0001

Data Index: 1102647 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 0.4160. Min Range: -0.4160

Max Act: 0.3814. Min Act: -0.0001

Data Index: 966228 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 0.4160. Min Range: -0.4160

Max Act: 0.3724. Min Act: -0.0001

Data Index: 174887 (C4 (Web Text))

Max Activating Token Index: 571

Text #8

Max Range: 0.4160. Min Range: -0.4160

Max Act: 0.3807. Min Act: -0.0001

Data Index: 174282 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 0.4160. Min Range: -0.4160

Max Act: 0.3753. Min Act: -0.0001

Data Index: 808612 (C4 (Web Text))

Max Activating Token Index: 533

Text #10

Max Range: 0.4160. Min Range: -0.4160

Max Act: 0.3702. Min Act: -0.0001

Data Index: 1079955 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 0.4160. Min Range: -0.4160

Max Act: 0.3765. Min Act: -0.0001

Data Index: 625272 (C4 (Web Text))

Max Activating Token Index: 652

Text #12

Max Range: 0.4160. Min Range: -0.4160

Max Act: 0.3803. Min Act: -0.0001

Data Index: 423214 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 0.4160. Min Range: -0.4160

Max Act: 0.3734. Min Act: -0.0001

Data Index: 1331928 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 0.4160. Min Range: -0.4160

Max Act: 0.3687. Min Act: -0.0001

Data Index: 58166 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 0.4160. Min Range: -0.4160

Max Act: 0.3709. Min Act: -0.0001

Data Index: 474583 (C4 (Web Text))

Max Activating Token Index: 612

Text #16

Max Range: 0.4160. Min Range: -0.4160

Max Act: 0.3707. Min Act: -0.0001

Data Index: 8329 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 0.4160. Min Range: -0.4160

Max Act: 0.3621. Min Act: -0.0001

Data Index: 307058 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 0.4160. Min Range: -0.4160

Max Act: 0.3594. Min Act: -0.0001

Data Index: 641328 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 0.4160. Min Range: -0.4160

Max Act: 0.3699. Min Act: -0.0001

Data Index: 580925 (C4 (Web Text))

Max Activating Token Index: 429