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

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

Neuron 207 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: 0.0970. Min Range: -0.0970

Max Act: 0.0970. Min Act: -0.0000

Data Index: 157475 (C4 (Web Text))

Max Activating Token Index: 549

Text #1

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0843. Min Act: -0.0000

Data Index: 43551 (C4 (Web Text))

Max Activating Token Index: 449

Text #2

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0846. Min Act: -0.0000

Data Index: 102681 (C4 (Web Text))

Max Activating Token Index: 390

Text #3

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0852. Min Act: -0.0000

Data Index: 216757 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0815. Min Act: -0.0000

Data Index: 222724 (C4 (Web Text))

Max Activating Token Index: 717

Text #5

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0793. Min Act: -0.0000

Data Index: 599073 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0713. Min Act: -0.0000

Data Index: 717245 (C4 (Web Text))

Max Activating Token Index: 415

Text #7

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0695. Min Act: -0.0000

Data Index: 959013 (C4 (Web Text))

Max Activating Token Index: 644

Text #8

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0734. Min Act: -0.0000

Data Index: 1237890 (C4 (Web Text))

Max Activating Token Index: 500

Text #9

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0710. Min Act: -0.0000

Data Index: 218717 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0699. Min Act: -0.0000

Data Index: 102821 (C4 (Web Text))

Max Activating Token Index: 340

Text #11

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0696. Min Act: -0.0000

Data Index: 1144545 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0713. Min Act: -0.0000

Data Index: 994314 (C4 (Web Text))

Max Activating Token Index: 426

Text #13

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0671. Min Act: -0.0000

Data Index: 186763 (C4 (Web Text))

Max Activating Token Index: 459

Text #14

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0683. Min Act: -0.0000

Data Index: 1122472 (C4 (Web Text))

Max Activating Token Index: 907

Text #15

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0602. Min Act: -0.0000

Data Index: 1160192 (C4 (Web Text))

Max Activating Token Index: 104

Text #16

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0626. Min Act: -0.0000

Data Index: 1093230 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0576. Min Act: -0.0000

Data Index: 334385 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0638. Min Act: -0.0000

Data Index: 979169 (C4 (Web Text))

Max Activating Token Index: 251

Text #19

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0600. Min Act: -0.0000

Data Index: 464915 (C4 (Web Text))

Max Activating Token Index: 323