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

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

Neuron 3614 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0564. Min Range: -3.0564

Max Act: 3.0564. Min Act: -0.0000

Data Index: 496228 (C4 (Web Text))

Max Activating Token Index: 644

Text #1

Max Range: 3.0564. Min Range: -3.0564

Max Act: 2.5853. Min Act: -0.0000

Data Index: 629463 (C4 (Web Text))

Max Activating Token Index: 523

Text #2

Max Range: 3.0564. Min Range: -3.0564

Max Act: 2.5150. Min Act: -0.0000

Data Index: 683290 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 3.0564. Min Range: -3.0564

Max Act: 2.4234. Min Act: -0.0000

Data Index: 1316144 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 3.0564. Min Range: -3.0564

Max Act: 2.3363. Min Act: -0.0000

Data Index: 243395 (C4 (Web Text))

Max Activating Token Index: 443

Text #5

Max Range: 3.0564. Min Range: -3.0564

Max Act: 2.4218. Min Act: -0.0000

Data Index: 122933 (C4 (Web Text))

Max Activating Token Index: 446

Text #6

Max Range: 3.0564. Min Range: -3.0564

Max Act: 2.3992. Min Act: -0.0000

Data Index: 1052997 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 3.0564. Min Range: -3.0564

Max Act: 2.3712. Min Act: -0.0000

Data Index: 652736 (C4 (Web Text))

Max Activating Token Index: 395

Text #8

Max Range: 3.0564. Min Range: -3.0564

Max Act: 2.2653. Min Act: -0.0000

Data Index: 681963 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 3.0564. Min Range: -3.0564

Max Act: 2.3731. Min Act: -0.0000

Data Index: 1129231 (C4 (Web Text))

Max Activating Token Index: 448

Text #10

Max Range: 3.0564. Min Range: -3.0564

Max Act: 2.2124. Min Act: -0.0000

Data Index: 182624 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 3.0564. Min Range: -3.0564

Max Act: 2.2343. Min Act: -0.0000

Data Index: 377533 (C4 (Web Text))

Max Activating Token Index: 1017

Text #12

Max Range: 3.0564. Min Range: -3.0564

Max Act: 2.1840. Min Act: -0.0000

Data Index: 432571 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 3.0564. Min Range: -3.0564

Max Act: 2.0991. Min Act: -0.0000

Data Index: 323306 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 3.0564. Min Range: -3.0564

Max Act: 2.2842. Min Act: -0.0000

Data Index: 674244 (C4 (Web Text))

Max Activating Token Index: 693

Text #15

Max Range: 3.0564. Min Range: -3.0564

Max Act: 2.0744. Min Act: -0.0000

Data Index: 1164260 (C4 (Web Text))

Max Activating Token Index: 965

Text #16

Max Range: 3.0564. Min Range: -3.0564

Max Act: 2.1637. Min Act: -0.0000

Data Index: 1129630 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 3.0564. Min Range: -3.0564

Max Act: 2.1619. Min Act: -0.0000

Data Index: 844499 (C4 (Web Text))

Max Activating Token Index: 766

Text #18

Max Range: 3.0564. Min Range: -3.0564

Max Act: 2.2789. Min Act: -0.0000

Data Index: 722707 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 3.0564. Min Range: -3.0564

Max Act: 2.2399. Min Act: -0.0000

Data Index: 317391 (C4 (Web Text))

Max Activating Token Index: 41