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

Dataset: The Pile

Neuron 1955 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.5031. Min Act: -0.0000

Data Index: 1628048 (The Pile)

Max Activating Token Index: 744

Text #1

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.5037. Min Act: -0.0000

Data Index: 1477593 (The Pile)

Max Activating Token Index: 341

Text #2

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.4540. Min Act: -0.0000

Data Index: 1090065 (The Pile)

Max Activating Token Index: 801

Text #3

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.4748. Min Act: -0.0000

Data Index: 567966 (The Pile)

Max Activating Token Index: 330

Text #4

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.4531. Min Act: -0.0000

Data Index: 1395046 (The Pile)

Max Activating Token Index: 567

Text #5

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.4344. Min Act: -0.0000

Data Index: 1160371 (The Pile)

Max Activating Token Index: 750

Text #6

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3907. Min Act: -0.0000

Data Index: 955579 (The Pile)

Max Activating Token Index: 743

Text #7

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.4264. Min Act: -0.0000

Data Index: 209248 (The Pile)

Max Activating Token Index: 143

Text #8

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3633. Min Act: -0.0000

Data Index: 1082827 (The Pile)

Max Activating Token Index: 942

Text #9

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3667. Min Act: -0.0000

Data Index: 63205 (The Pile)

Max Activating Token Index: 335

Text #10

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3688. Min Act: -0.0000

Data Index: 223220 (The Pile)

Max Activating Token Index: 195

Text #11

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3604. Min Act: -0.0000

Data Index: 337165 (The Pile)

Max Activating Token Index: 969

Text #12

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3755. Min Act: -0.0000

Data Index: 630764 (The Pile)

Max Activating Token Index: 507

Text #13

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3680. Min Act: -0.0000

Data Index: 792651 (The Pile)

Max Activating Token Index: 708

Text #14

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3578. Min Act: -0.0000

Data Index: 1640024 (The Pile)

Max Activating Token Index: 275

Text #15

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3416. Min Act: -0.0000

Data Index: 1865651 (The Pile)

Max Activating Token Index: 84

Text #16

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3524. Min Act: -0.0000

Data Index: 933100 (The Pile)

Max Activating Token Index: 300

Text #17

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3717. Min Act: -0.0000

Data Index: 516688 (The Pile)

Max Activating Token Index: 741

Text #18

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3239. Min Act: -0.0000

Data Index: 1848756 (The Pile)

Max Activating Token Index: 666

Text #19

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3896. Min Act: -0.0000

Data Index: 1550022 (The Pile)

Max Activating Token Index: 24