Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1845 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.6513. Min Act: -0.0001

Data Index: 578411 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5771. Min Act: -0.0001

Data Index: 595193 (C4 (Web Text))

Max Activating Token Index: 377

Text #2

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5766. Min Act: -0.0001

Data Index: 1053192 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5724. Min Act: -0.0001

Data Index: 153989 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5609. Min Act: -0.0001

Data Index: 1244160 (C4 (Web Text))

Max Activating Token Index: 352

Text #5

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5604. Min Act: -0.0001

Data Index: 1283666 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5184. Min Act: -0.0001

Data Index: 802685 (C4 (Web Text))

Max Activating Token Index: 674

Text #7

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5338. Min Act: -0.0001

Data Index: 203117 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5309. Min Act: -0.0001

Data Index: 974132 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5304. Min Act: -0.0001

Data Index: 259213 (C4 (Web Text))

Max Activating Token Index: 761

Text #10

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5232. Min Act: -0.0001

Data Index: 1351204 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5390. Min Act: -0.0001

Data Index: 784867 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5034. Min Act: -0.0001

Data Index: 433029 (C4 (Web Text))

Max Activating Token Index: 335

Text #13

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5156. Min Act: -0.0001

Data Index: 1274008 (C4 (Web Text))

Max Activating Token Index: 445

Text #14

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5082. Min Act: -0.0001

Data Index: 456456 (C4 (Web Text))

Max Activating Token Index: 583

Text #15

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5140. Min Act: -0.0001

Data Index: 177880 (C4 (Web Text))

Max Activating Token Index: 715

Text #16

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.4909. Min Act: -0.0001

Data Index: 1221610 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5051. Min Act: -0.0001

Data Index: 769484 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5057. Min Act: -0.0001

Data Index: 695418 (C4 (Web Text))

Max Activating Token Index: 101

Text #19

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5017. Min Act: -0.0001

Data Index: 87347 (C4 (Web Text))

Max Activating Token Index: 170