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

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

Neuron 2998 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.6807. Min Range: -7.6807

Max Act: 7.3581. Min Act: -0.0000

Data Index: 1189372 (C4 (Web Text))

Max Activating Token Index: 272

Text #1

Max Range: 7.6807. Min Range: -7.6807

Max Act: 7.6807. Min Act: -0.0000

Data Index: 534698 (C4 (Web Text))

Max Activating Token Index: 423

Text #2

Max Range: 7.6807. Min Range: -7.6807

Max Act: 7.3210. Min Act: -0.0000

Data Index: 538339 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 7.6807. Min Range: -7.6807

Max Act: 7.0938. Min Act: -0.0000

Data Index: 1034459 (C4 (Web Text))

Max Activating Token Index: 1001

Text #4

Max Range: 7.6807. Min Range: -7.6807

Max Act: 7.4597. Min Act: -0.0000

Data Index: 1333942 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 7.6807. Min Range: -7.6807

Max Act: 7.3726. Min Act: -0.0000

Data Index: 906419 (C4 (Web Text))

Max Activating Token Index: 443

Text #6

Max Range: 7.6807. Min Range: -7.6807

Max Act: 6.8024. Min Act: -0.0000

Data Index: 335076 (C4 (Web Text))

Max Activating Token Index: 638

Text #7

Max Range: 7.6807. Min Range: -7.6807

Max Act: 7.0377. Min Act: -0.0000

Data Index: 618873 (C4 (Web Text))

Max Activating Token Index: 389

Text #8

Max Range: 7.6807. Min Range: -7.6807

Max Act: 6.5927. Min Act: -0.0000

Data Index: 1048088 (C4 (Web Text))

Max Activating Token Index: 760

Text #9

Max Range: 7.6807. Min Range: -7.6807

Max Act: 6.8424. Min Act: -0.0000

Data Index: 1033274 (C4 (Web Text))

Max Activating Token Index: 403

Text #10

Max Range: 7.6807. Min Range: -7.6807

Max Act: 6.2473. Min Act: -0.0000

Data Index: 876327 (C4 (Web Text))

Max Activating Token Index: 207

Text #11

Max Range: 7.6807. Min Range: -7.6807

Max Act: 6.2663. Min Act: -0.0000

Data Index: 448068 (C4 (Web Text))

Max Activating Token Index: 464

Text #12

Max Range: 7.6807. Min Range: -7.6807

Max Act: 6.4050. Min Act: -0.0000

Data Index: 45613 (C4 (Web Text))

Max Activating Token Index: 214

Text #13

Max Range: 7.6807. Min Range: -7.6807

Max Act: 6.1590. Min Act: -0.0000

Data Index: 540629 (C4 (Web Text))

Max Activating Token Index: 312

Text #14

Max Range: 7.6807. Min Range: -7.6807

Max Act: 5.9725. Min Act: -0.0000

Data Index: 1140370 (C4 (Web Text))

Max Activating Token Index: 940

Text #15

Max Range: 7.6807. Min Range: -7.6807

Max Act: 5.4740. Min Act: -0.0000

Data Index: 1254696 (C4 (Web Text))

Max Activating Token Index: 633

Text #16

Max Range: 7.6807. Min Range: -7.6807

Max Act: 5.5259. Min Act: -0.0000

Data Index: 116795 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 7.6807. Min Range: -7.6807

Max Act: 5.3472. Min Act: -0.0000

Data Index: 155216 (C4 (Web Text))

Max Activating Token Index: 222

Text #18

Max Range: 7.6807. Min Range: -7.6807

Max Act: 5.1044. Min Act: -0.0000

Data Index: 754008 (C4 (Web Text))

Max Activating Token Index: 359

Text #19

Max Range: 7.6807. Min Range: -7.6807

Max Act: 5.3993. Min Act: -0.0000

Data Index: 1023443 (C4 (Web Text))

Max Activating Token Index: 113