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

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

Neuron 4365 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0773. Min Range: -1.0773

Max Act: 1.0773. Min Act: -0.0000

Data Index: 1002051 (C4 (Web Text))

Max Activating Token Index: 681

Text #1

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.9841. Min Act: -0.0000

Data Index: 1299365 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.9541. Min Act: -0.0000

Data Index: 1470018 (Python Code)

Max Activating Token Index: 1022

Text #3

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.9517. Min Act: -0.0000

Data Index: 1440183 (Python Code)

Max Activating Token Index: 592

Text #4

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.9719. Min Act: -0.0000

Data Index: 1571156 (Python Code)

Max Activating Token Index: 1019

Text #5

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.9005. Min Act: -0.0000

Data Index: 1616343 (Python Code)

Max Activating Token Index: 559

Text #6

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.8953. Min Act: -0.0000

Data Index: 1572671 (Python Code)

Max Activating Token Index: 269

Text #7

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.9006. Min Act: -0.0000

Data Index: 1652098 (Python Code)

Max Activating Token Index: 425

Text #8

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.9167. Min Act: -0.0000

Data Index: 923393 (C4 (Web Text))

Max Activating Token Index: 605

Text #9

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.8600. Min Act: -0.0000

Data Index: 279134 (C4 (Web Text))

Max Activating Token Index: 811

Text #10

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.9070. Min Act: -0.0000

Data Index: 1205711 (C4 (Web Text))

Max Activating Token Index: 101

Text #11

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.8756. Min Act: -0.0000

Data Index: 623600 (C4 (Web Text))

Max Activating Token Index: 213

Text #12

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.8797. Min Act: -0.0000

Data Index: 1399889 (Python Code)

Max Activating Token Index: 576

Text #13

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.8312. Min Act: -0.0000

Data Index: 24895 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.8225. Min Act: -0.0000

Data Index: 603785 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.8728. Min Act: -0.0000

Data Index: 776192 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.8535. Min Act: -0.0000

Data Index: 1484915 (Python Code)

Max Activating Token Index: 311

Text #17

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.8121. Min Act: -0.0000

Data Index: 345048 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.7585. Min Act: 0.0000

Data Index: 359354 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.8070. Min Act: -0.0000

Data Index: 764730 (C4 (Web Text))

Max Activating Token Index: 330