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

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

Neuron 454 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.5408. Min Act: -0.0000

Data Index: 56089 (C4 (Web Text))

Max Activating Token Index: 908

Text #1

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.5352. Min Act: -0.0000

Data Index: 567297 (C4 (Web Text))

Max Activating Token Index: 464

Text #2

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.5033. Min Act: 0.0000

Data Index: 936374 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4811. Min Act: -0.0000

Data Index: 1114589 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4772. Min Act: 0.0000

Data Index: 879699 (C4 (Web Text))

Max Activating Token Index: 880

Text #5

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4582. Min Act: -0.0000

Data Index: 1167408 (C4 (Web Text))

Max Activating Token Index: 462

Text #6

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4605. Min Act: -0.0000

Data Index: 373044 (C4 (Web Text))

Max Activating Token Index: 275

Text #7

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4517. Min Act: 0.0000

Data Index: 225644 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4043. Min Act: -0.0000

Data Index: 770040 (C4 (Web Text))

Max Activating Token Index: 702

Text #9

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4492. Min Act: 0.0000

Data Index: 786692 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4584. Min Act: -0.0000

Data Index: 741258 (C4 (Web Text))

Max Activating Token Index: 919

Text #11

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4399. Min Act: 0.0000

Data Index: 766552 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4273. Min Act: -0.0000

Data Index: 1327133 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4327. Min Act: 0.0000

Data Index: 1222661 (C4 (Web Text))

Max Activating Token Index: 1022

Text #14

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4335. Min Act: 0.0000

Data Index: 648749 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4453. Min Act: -0.0000

Data Index: 410799 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4313. Min Act: -0.0000

Data Index: 907396 (C4 (Web Text))

Max Activating Token Index: 976

Text #17

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4227. Min Act: -0.0000

Data Index: 1011965 (C4 (Web Text))

Max Activating Token Index: 137

Text #18

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4105. Min Act: -0.0000

Data Index: 422089 (C4 (Web Text))

Max Activating Token Index: 441

Text #19

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4220. Min Act: -0.0000

Data Index: 507882 (C4 (Web Text))

Max Activating Token Index: 294