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

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

Neuron 3446 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0440. Min Range: -1.0440

Max Act: 1.0440. Min Act: -0.0001

Data Index: 196065 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.9708. Min Act: -0.0001

Data Index: 1101712 (C4 (Web Text))

Max Activating Token Index: 611

Text #2

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.9418. Min Act: -0.0001

Data Index: 669134 (C4 (Web Text))

Max Activating Token Index: 160

Text #3

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.9654. Min Act: -0.0001

Data Index: 1525152 (Python Code)

Max Activating Token Index: 454

Text #4

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.9972. Min Act: -0.0001

Data Index: 287103 (C4 (Web Text))

Max Activating Token Index: 386

Text #5

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.8218. Min Act: -0.0001

Data Index: 505773 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.8605. Min Act: -0.0001

Data Index: 262735 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.8056. Min Act: -0.0001

Data Index: 890544 (C4 (Web Text))

Max Activating Token Index: 761

Text #8

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.7671. Min Act: -0.0001

Data Index: 206790 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.8378. Min Act: -0.0001

Data Index: 775427 (C4 (Web Text))

Max Activating Token Index: 683

Text #10

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.8000. Min Act: -0.0001

Data Index: 1023901 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.8072. Min Act: -0.0001

Data Index: 719244 (C4 (Web Text))

Max Activating Token Index: 486

Text #12

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.7026. Min Act: -0.0001

Data Index: 1181459 (C4 (Web Text))

Max Activating Token Index: 569

Text #13

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.9174. Min Act: -0.0001

Data Index: 605865 (C4 (Web Text))

Max Activating Token Index: 232

Text #14

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.8109. Min Act: -0.0001

Data Index: 628750 (C4 (Web Text))

Max Activating Token Index: 2

Text #15

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.8115. Min Act: -0.0001

Data Index: 571953 (C4 (Web Text))

Max Activating Token Index: 287

Text #16

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.7849. Min Act: -0.0001

Data Index: 603627 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.8008. Min Act: -0.0001

Data Index: 744376 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.8190. Min Act: -0.0001

Data Index: 813816 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.7722. Min Act: -0.0001

Data Index: 325259 (C4 (Web Text))

Max Activating Token Index: 431