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

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

Neuron 414 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0827. Min Act: -0.0001

Data Index: 1224379 (C4 (Web Text))

Max Activating Token Index: 841

Text #1

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0799. Min Act: -0.0001

Data Index: 84578 (C4 (Web Text))

Max Activating Token Index: 913

Text #2

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0722. Min Act: -0.0001

Data Index: 1569220 (Python Code)

Max Activating Token Index: 425

Text #3

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0691. Min Act: -0.0001

Data Index: 1129781 (C4 (Web Text))

Max Activating Token Index: 465

Text #4

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0629. Min Act: -0.0001

Data Index: 1091340 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0664. Min Act: -0.0001

Data Index: 1505888 (Python Code)

Max Activating Token Index: 273

Text #6

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0627. Min Act: -0.0001

Data Index: 208412 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0599. Min Act: -0.0001

Data Index: 1457740 (Python Code)

Max Activating Token Index: 437

Text #8

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0666. Min Act: -0.0001

Data Index: 510531 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0626. Min Act: -0.0001

Data Index: 605288 (C4 (Web Text))

Max Activating Token Index: 598

Text #10

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0578. Min Act: -0.0001

Data Index: 646449 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0595. Min Act: -0.0001

Data Index: 1354919 (C4 (Web Text))

Max Activating Token Index: 185

Text #12

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0621. Min Act: -0.0001

Data Index: 439903 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0615. Min Act: -0.0001

Data Index: 535521 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0590. Min Act: -0.0001

Data Index: 777105 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0560. Min Act: -0.0001

Data Index: 816557 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0560. Min Act: -0.0001

Data Index: 255345 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0580. Min Act: -0.0001

Data Index: 531445 (C4 (Web Text))

Max Activating Token Index: 8

Text #18

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0628. Min Act: -0.0001

Data Index: 718204 (C4 (Web Text))

Max Activating Token Index: 611

Text #19

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0580. Min Act: -0.0001

Data Index: 859712 (C4 (Web Text))

Max Activating Token Index: 8