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

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

Neuron 3205 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8324. Min Range: -1.8324

Max Act: 1.8324. Min Act: -0.0002

Data Index: 640430 (C4 (Web Text))

Max Activating Token Index: 505

Text #1

Max Range: 1.8324. Min Range: -1.8324

Max Act: 1.4628. Min Act: -0.0002

Data Index: 1293742 (C4 (Web Text))

Max Activating Token Index: 369

Text #2

Max Range: 1.8324. Min Range: -1.8324

Max Act: 1.4816. Min Act: -0.0002

Data Index: 817363 (C4 (Web Text))

Max Activating Token Index: 658

Text #3

Max Range: 1.8324. Min Range: -1.8324

Max Act: 1.2347. Min Act: -0.0002

Data Index: 1236556 (C4 (Web Text))

Max Activating Token Index: 270

Text #4

Max Range: 1.8324. Min Range: -1.8324

Max Act: 1.1801. Min Act: -0.0002

Data Index: 215221 (C4 (Web Text))

Max Activating Token Index: 89

Text #5

Max Range: 1.8324. Min Range: -1.8324

Max Act: 1.1336. Min Act: -0.0002

Data Index: 1170070 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 1.8324. Min Range: -1.8324

Max Act: 1.1002. Min Act: -0.0002

Data Index: 242226 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 1.8324. Min Range: -1.8324

Max Act: 1.1181. Min Act: -0.0002

Data Index: 526763 (C4 (Web Text))

Max Activating Token Index: 629

Text #8

Max Range: 1.8324. Min Range: -1.8324

Max Act: 1.0888. Min Act: -0.0002

Data Index: 925130 (C4 (Web Text))

Max Activating Token Index: 361

Text #9

Max Range: 1.8324. Min Range: -1.8324

Max Act: 1.1039. Min Act: -0.0002

Data Index: 910089 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 1.8324. Min Range: -1.8324

Max Act: 1.0706. Min Act: -0.0002

Data Index: 625551 (C4 (Web Text))

Max Activating Token Index: 994

Text #11

Max Range: 1.8324. Min Range: -1.8324

Max Act: 0.9953. Min Act: -0.0002

Data Index: 927000 (C4 (Web Text))

Max Activating Token Index: 391

Text #12

Max Range: 1.8324. Min Range: -1.8324

Max Act: 1.0377. Min Act: -0.0002

Data Index: 1225474 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 1.8324. Min Range: -1.8324

Max Act: 1.0814. Min Act: -0.0002

Data Index: 643388 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 1.8324. Min Range: -1.8324

Max Act: 1.0211. Min Act: -0.0002

Data Index: 277733 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 1.8324. Min Range: -1.8324

Max Act: 0.9774. Min Act: -0.0002

Data Index: 130470 (C4 (Web Text))

Max Activating Token Index: 546

Text #16

Max Range: 1.8324. Min Range: -1.8324

Max Act: 0.9636. Min Act: -0.0002

Data Index: 1305270 (C4 (Web Text))

Max Activating Token Index: 198

Text #17

Max Range: 1.8324. Min Range: -1.8324

Max Act: 0.9594. Min Act: -0.0002

Data Index: 320160 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 1.8324. Min Range: -1.8324

Max Act: 0.9297. Min Act: -0.0002

Data Index: 1035663 (C4 (Web Text))

Max Activating Token Index: 493

Text #19

Max Range: 1.8324. Min Range: -1.8324

Max Act: 0.9201. Min Act: -0.0002

Data Index: 938321 (C4 (Web Text))

Max Activating Token Index: 554