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

Dataset: The Pile

Neuron 1146 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.7426. Min Act: -0.0000

Data Index: 891714 (The Pile)

Max Activating Token Index: 980

Text #1

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.6164. Min Act: -0.0000

Data Index: 38478 (The Pile)

Max Activating Token Index: 650

Text #2

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.5850. Min Act: -0.0000

Data Index: 444217 (The Pile)

Max Activating Token Index: 662

Text #3

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.4770. Min Act: -0.0000

Data Index: 1653821 (The Pile)

Max Activating Token Index: 271

Text #4

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.4707. Min Act: -0.0000

Data Index: 43143 (The Pile)

Max Activating Token Index: 42

Text #5

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.4416. Min Act: -0.0000

Data Index: 1929016 (The Pile)

Max Activating Token Index: 293

Text #6

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.4336. Min Act: -0.0000

Data Index: 672629 (The Pile)

Max Activating Token Index: 242

Text #7

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.4571. Min Act: -0.0000

Data Index: 1377653 (The Pile)

Max Activating Token Index: 758

Text #8

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.3981. Min Act: -0.0000

Data Index: 1449870 (The Pile)

Max Activating Token Index: 673

Text #9

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.4317. Min Act: -0.0000

Data Index: 683149 (The Pile)

Max Activating Token Index: 957

Text #10

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.3796. Min Act: -0.0000

Data Index: 233616 (The Pile)

Max Activating Token Index: 753

Text #11

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.3825. Min Act: -0.0000

Data Index: 1303403 (The Pile)

Max Activating Token Index: 201

Text #12

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.3759. Min Act: -0.0000

Data Index: 449936 (The Pile)

Max Activating Token Index: 345

Text #13

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.3529. Min Act: -0.0000

Data Index: 273815 (The Pile)

Max Activating Token Index: 790

Text #14

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.3733. Min Act: -0.0000

Data Index: 743267 (The Pile)

Max Activating Token Index: 347

Text #15

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.3442. Min Act: -0.0000

Data Index: 1862785 (The Pile)

Max Activating Token Index: 801

Text #16

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.3913. Min Act: -0.0000

Data Index: 404718 (The Pile)

Max Activating Token Index: 243

Text #17

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.3942. Min Act: -0.0000

Data Index: 1811702 (The Pile)

Max Activating Token Index: 296

Text #18

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.3564. Min Act: -0.0000

Data Index: 1863157 (The Pile)

Max Activating Token Index: 709

Text #19

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.3392. Min Act: -0.0000

Data Index: 445862 (The Pile)

Max Activating Token Index: 157