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

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

Neuron 970 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: 0.7306. Min Range: -0.7306

Max Act: 0.7306. Min Act: -0.0003

Data Index: 535482 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.5834. Min Act: -0.0003

Data Index: 1192255 (C4 (Web Text))

Max Activating Token Index: 634

Text #2

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.5776. Min Act: -0.0003

Data Index: 1067391 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.5102. Min Act: -0.0003

Data Index: 999880 (C4 (Web Text))

Max Activating Token Index: 481

Text #4

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.5271. Min Act: -0.0003

Data Index: 47123 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.4876. Min Act: -0.0002

Data Index: 698627 (C4 (Web Text))

Max Activating Token Index: 548

Text #6

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.4966. Min Act: -0.0003

Data Index: 261416 (C4 (Web Text))

Max Activating Token Index: 397

Text #7

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.5039. Min Act: -0.0003

Data Index: 841397 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.4499. Min Act: -0.0003

Data Index: 403952 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.4749. Min Act: -0.0002

Data Index: 438005 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.4420. Min Act: -0.0003

Data Index: 812724 (C4 (Web Text))

Max Activating Token Index: 310

Text #11

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.4739. Min Act: -0.0003

Data Index: 465222 (C4 (Web Text))

Max Activating Token Index: 143

Text #12

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.4790. Min Act: -0.0003

Data Index: 1002847 (C4 (Web Text))

Max Activating Token Index: 127

Text #13

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.4432. Min Act: -0.0003

Data Index: 961128 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.4355. Min Act: -0.0003

Data Index: 581402 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.4018. Min Act: -0.0003

Data Index: 864393 (C4 (Web Text))

Max Activating Token Index: 99

Text #16

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.4602. Min Act: -0.0003

Data Index: 875747 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.4410. Min Act: -0.0003

Data Index: 126317 (C4 (Web Text))

Max Activating Token Index: 455

Text #18

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.4389. Min Act: -0.0002

Data Index: 479197 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.4050. Min Act: -0.0003

Data Index: 648780 (C4 (Web Text))

Max Activating Token Index: 242