Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3880 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.4485. Min Act: -0.0003

Data Index: 996779 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.4296. Min Act: -0.0003

Data Index: 915501 (C4 (Web Text))

Max Activating Token Index: 768

Text #2

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.4152. Min Act: -0.0003

Data Index: 1093949 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.4201. Min Act: -0.0003

Data Index: 1156909 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.4102. Min Act: -0.0003

Data Index: 1001946 (C4 (Web Text))

Max Activating Token Index: 654

Text #5

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3901. Min Act: -0.0003

Data Index: 36024 (C4 (Web Text))

Max Activating Token Index: 207

Text #6

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3961. Min Act: -0.0003

Data Index: 1197470 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3959. Min Act: -0.0003

Data Index: 535417 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3911. Min Act: -0.0003

Data Index: 442040 (C4 (Web Text))

Max Activating Token Index: 717

Text #9

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3711. Min Act: -0.0003

Data Index: 708949 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3816. Min Act: -0.0003

Data Index: 796757 (C4 (Web Text))

Max Activating Token Index: 884

Text #11

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3850. Min Act: -0.0003

Data Index: 319788 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3699. Min Act: -0.0003

Data Index: 472827 (C4 (Web Text))

Max Activating Token Index: 293

Text #13

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3688. Min Act: -0.0003

Data Index: 436389 (C4 (Web Text))

Max Activating Token Index: 468

Text #14

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3829. Min Act: -0.0003

Data Index: 279753 (C4 (Web Text))

Max Activating Token Index: 134

Text #15

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3808. Min Act: -0.0003

Data Index: 480639 (C4 (Web Text))

Max Activating Token Index: 146

Text #16

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3905. Min Act: -0.0003

Data Index: 1014607 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3758. Min Act: -0.0003

Data Index: 1095234 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3642. Min Act: -0.0003

Data Index: 726161 (C4 (Web Text))

Max Activating Token Index: 322

Text #19

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3885. Min Act: -0.0003

Data Index: 637328 (C4 (Web Text))

Max Activating Token Index: 467