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

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

Neuron 3427 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1311. Min Act: -0.0002

Data Index: 395052 (C4 (Web Text))

Max Activating Token Index: 438

Text #1

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1082. Min Act: -0.0002

Data Index: 294548 (C4 (Web Text))

Max Activating Token Index: 566

Text #2

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0957. Min Act: -0.0002

Data Index: 1035236 (C4 (Web Text))

Max Activating Token Index: 462

Text #3

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0935. Min Act: -0.0002

Data Index: 776115 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0961. Min Act: -0.0002

Data Index: 712574 (C4 (Web Text))

Max Activating Token Index: 744

Text #5

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0889. Min Act: -0.0002

Data Index: 145799 (C4 (Web Text))

Max Activating Token Index: 408

Text #6

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0864. Min Act: -0.0002

Data Index: 555391 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0902. Min Act: -0.0002

Data Index: 1318180 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0920. Min Act: -0.0002

Data Index: 123213 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0802. Min Act: -0.0002

Data Index: 1323478 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0824. Min Act: -0.0002

Data Index: 678784 (C4 (Web Text))

Max Activating Token Index: 464

Text #11

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0833. Min Act: -0.0002

Data Index: 1331947 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0788. Min Act: -0.0002

Data Index: 1320394 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0852. Min Act: -0.0002

Data Index: 1264489 (C4 (Web Text))

Max Activating Token Index: 780

Text #14

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0809. Min Act: -0.0002

Data Index: 802552 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0767. Min Act: -0.0002

Data Index: 441702 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0767. Min Act: -0.0002

Data Index: 314881 (C4 (Web Text))

Max Activating Token Index: 298

Text #17

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0759. Min Act: -0.0002

Data Index: 527655 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0781. Min Act: -0.0002

Data Index: 149576 (C4 (Web Text))

Max Activating Token Index: 818

Text #19

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0785. Min Act: -0.0002

Data Index: 1286633 (C4 (Web Text))

Max Activating Token Index: 262