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

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

Neuron 4804 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: 1.2494. Min Range: -1.2494

Max Act: 1.2206. Min Act: -0.0002

Data Index: 128596 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 1.2494. Min Range: -1.2494

Max Act: 1.2494. Min Act: -0.0002

Data Index: 1098562 (C4 (Web Text))

Max Activating Token Index: 82

Text #2

Max Range: 1.2494. Min Range: -1.2494

Max Act: 1.1806. Min Act: -0.0002

Data Index: 216682 (C4 (Web Text))

Max Activating Token Index: 551

Text #3

Max Range: 1.2494. Min Range: -1.2494

Max Act: 1.1714. Min Act: -0.0002

Data Index: 820445 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 1.2494. Min Range: -1.2494

Max Act: 1.1714. Min Act: -0.0002

Data Index: 391021 (C4 (Web Text))

Max Activating Token Index: 3

Text #5

Max Range: 1.2494. Min Range: -1.2494

Max Act: 1.0471. Min Act: -0.0002

Data Index: 150497 (C4 (Web Text))

Max Activating Token Index: 947

Text #6

Max Range: 1.2494. Min Range: -1.2494

Max Act: 1.0146. Min Act: -0.0002

Data Index: 93284 (C4 (Web Text))

Max Activating Token Index: 631

Text #7

Max Range: 1.2494. Min Range: -1.2494

Max Act: 1.0349. Min Act: -0.0002

Data Index: 242438 (C4 (Web Text))

Max Activating Token Index: 3

Text #8

Max Range: 1.2494. Min Range: -1.2494

Max Act: 1.0349. Min Act: -0.0002

Data Index: 429988 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 1.2494. Min Range: -1.2494

Max Act: 0.9707. Min Act: -0.0002

Data Index: 1059952 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 1.2494. Min Range: -1.2494

Max Act: 0.9693. Min Act: -0.0002

Data Index: 163313 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 1.2494. Min Range: -1.2494

Max Act: 0.9668. Min Act: -0.0002

Data Index: 317344 (C4 (Web Text))

Max Activating Token Index: 933

Text #12

Max Range: 1.2494. Min Range: -1.2494

Max Act: 0.9757. Min Act: -0.0002

Data Index: 372775 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 1.2494. Min Range: -1.2494

Max Act: 1.0065. Min Act: -0.0002

Data Index: 332185 (C4 (Web Text))

Max Activating Token Index: 4

Text #14

Max Range: 1.2494. Min Range: -1.2494

Max Act: 0.8977. Min Act: -0.0002

Data Index: 20717 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 1.2494. Min Range: -1.2494

Max Act: 0.9496. Min Act: -0.0002

Data Index: 1082757 (C4 (Web Text))

Max Activating Token Index: 382

Text #16

Max Range: 1.2494. Min Range: -1.2494

Max Act: 1.0327. Min Act: -0.0002

Data Index: 134458 (C4 (Web Text))

Max Activating Token Index: 80

Text #17

Max Range: 1.2494. Min Range: -1.2494

Max Act: 1.0273. Min Act: -0.0002

Data Index: 933037 (C4 (Web Text))

Max Activating Token Index: 606

Text #18

Max Range: 1.2494. Min Range: -1.2494

Max Act: 0.9112. Min Act: -0.0002

Data Index: 677596 (C4 (Web Text))

Max Activating Token Index: 651

Text #19

Max Range: 1.2494. Min Range: -1.2494

Max Act: 0.9421. Min Act: -0.0002

Data Index: 670020 (C4 (Web Text))

Max Activating Token Index: 237