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

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

Neuron 3981 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6149. Min Range: -1.6149

Max Act: 1.6149. Min Act: -0.0001

Data Index: 690409 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 1.6149. Min Range: -1.6149

Max Act: 1.4989. Min Act: -0.0000

Data Index: 138209 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 1.6149. Min Range: -1.6149

Max Act: 1.3716. Min Act: -0.0001

Data Index: 298229 (C4 (Web Text))

Max Activating Token Index: 737

Text #3

Max Range: 1.6149. Min Range: -1.6149

Max Act: 1.5551. Min Act: -0.0001

Data Index: 502146 (C4 (Web Text))

Max Activating Token Index: 446

Text #4

Max Range: 1.6149. Min Range: -1.6149

Max Act: 1.3103. Min Act: -0.0000

Data Index: 844474 (C4 (Web Text))

Max Activating Token Index: 810

Text #5

Max Range: 1.6149. Min Range: -1.6149

Max Act: 1.1578. Min Act: -0.0001

Data Index: 62576 (C4 (Web Text))

Max Activating Token Index: 865

Text #6

Max Range: 1.6149. Min Range: -1.6149

Max Act: 1.2543. Min Act: -0.0000

Data Index: 583162 (C4 (Web Text))

Max Activating Token Index: 385

Text #7

Max Range: 1.6149. Min Range: -1.6149

Max Act: 1.1909. Min Act: -0.0001

Data Index: 717139 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 1.6149. Min Range: -1.6149

Max Act: 1.2054. Min Act: -0.0001

Data Index: 264358 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 1.6149. Min Range: -1.6149

Max Act: 1.1565. Min Act: -0.0001

Data Index: 1071488 (C4 (Web Text))

Max Activating Token Index: 918

Text #10

Max Range: 1.6149. Min Range: -1.6149

Max Act: 1.0387. Min Act: -0.0001

Data Index: 509409 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 1.6149. Min Range: -1.6149

Max Act: 1.0936. Min Act: -0.0000

Data Index: 368901 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 1.6149. Min Range: -1.6149

Max Act: 1.0924. Min Act: -0.0001

Data Index: 1287544 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 1.6149. Min Range: -1.6149

Max Act: 1.0789. Min Act: -0.0000

Data Index: 1460216 (Python Code)

Max Activating Token Index: 536

Text #14

Max Range: 1.6149. Min Range: -1.6149

Max Act: 1.0871. Min Act: -0.0001

Data Index: 1089382 (C4 (Web Text))

Max Activating Token Index: 666

Text #15

Max Range: 1.6149. Min Range: -1.6149

Max Act: 1.0712. Min Act: -0.0000

Data Index: 189762 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 1.6149. Min Range: -1.6149

Max Act: 1.0436. Min Act: -0.0001

Data Index: 967681 (C4 (Web Text))

Max Activating Token Index: 557

Text #17

Max Range: 1.6149. Min Range: -1.6149

Max Act: 1.1284. Min Act: -0.0001

Data Index: 983463 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 1.6149. Min Range: -1.6149

Max Act: 1.1246. Min Act: -0.0001

Data Index: 951912 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 1.6149. Min Range: -1.6149

Max Act: 1.0849. Min Act: -0.0001

Data Index: 1206492 (C4 (Web Text))

Max Activating Token Index: 674