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

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

Neuron 31 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0595. Min Range: -2.0595

Max Act: 2.0595. Min Act: -0.0000

Data Index: 664486 (C4 (Web Text))

Max Activating Token Index: 585

Text #1

Max Range: 2.0595. Min Range: -2.0595

Max Act: 1.6197. Min Act: -0.0000

Data Index: 266346 (C4 (Web Text))

Max Activating Token Index: 840

Text #2

Max Range: 2.0595. Min Range: -2.0595

Max Act: 1.6007. Min Act: -0.0000

Data Index: 992213 (C4 (Web Text))

Max Activating Token Index: 430

Text #3

Max Range: 2.0595. Min Range: -2.0595

Max Act: 1.5885. Min Act: -0.0000

Data Index: 626030 (C4 (Web Text))

Max Activating Token Index: 872

Text #4

Max Range: 2.0595. Min Range: -2.0595

Max Act: 1.6658. Min Act: -0.0000

Data Index: 286359 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 2.0595. Min Range: -2.0595

Max Act: 1.5136. Min Act: -0.0000

Data Index: 352950 (C4 (Web Text))

Max Activating Token Index: 856

Text #6

Max Range: 2.0595. Min Range: -2.0595

Max Act: 1.4000. Min Act: -0.0000

Data Index: 918822 (C4 (Web Text))

Max Activating Token Index: 882

Text #7

Max Range: 2.0595. Min Range: -2.0595

Max Act: 1.3028. Min Act: -0.0000

Data Index: 305860 (C4 (Web Text))

Max Activating Token Index: 955

Text #8

Max Range: 2.0595. Min Range: -2.0595

Max Act: 1.3966. Min Act: -0.0000

Data Index: 703350 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 2.0595. Min Range: -2.0595

Max Act: 1.3441. Min Act: -0.0000

Data Index: 505142 (C4 (Web Text))

Max Activating Token Index: 705

Text #10

Max Range: 2.0595. Min Range: -2.0595

Max Act: 1.1686. Min Act: -0.0000

Data Index: 1251536 (C4 (Web Text))

Max Activating Token Index: 124

Text #11

Max Range: 2.0595. Min Range: -2.0595

Max Act: 1.2321. Min Act: -0.0000

Data Index: 273531 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 2.0595. Min Range: -2.0595

Max Act: 1.0574. Min Act: -0.0000

Data Index: 855299 (C4 (Web Text))

Max Activating Token Index: 337

Text #13

Max Range: 2.0595. Min Range: -2.0595

Max Act: 1.0742. Min Act: -0.0000

Data Index: 1198831 (C4 (Web Text))

Max Activating Token Index: 1003

Text #14

Max Range: 2.0595. Min Range: -2.0595

Max Act: 1.1026. Min Act: -0.0000

Data Index: 1099564 (C4 (Web Text))

Max Activating Token Index: 115

Text #15

Max Range: 2.0595. Min Range: -2.0595

Max Act: 1.0086. Min Act: -0.0000

Data Index: 906939 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 2.0595. Min Range: -2.0595

Max Act: 1.0339. Min Act: -0.0000

Data Index: 106442 (C4 (Web Text))

Max Activating Token Index: 36

Text #17

Max Range: 2.0595. Min Range: -2.0595

Max Act: 1.0205. Min Act: -0.0000

Data Index: 510084 (C4 (Web Text))

Max Activating Token Index: 953

Text #18

Max Range: 2.0595. Min Range: -2.0595

Max Act: 1.0252. Min Act: -0.0000

Data Index: 564578 (C4 (Web Text))

Max Activating Token Index: 283

Text #19

Max Range: 2.0595. Min Range: -2.0595

Max Act: 1.0499. Min Act: -0.0000

Data Index: 1275530 (C4 (Web Text))

Max Activating Token Index: 795