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

Dataset: The Pile

Neuron 4456 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2539. Min Range: -3.2539

Max Act: 3.2539. Min Act: -0.0000

Data Index: 258079 (The Pile)

Max Activating Token Index: 449

Text #1

Max Range: 3.2539. Min Range: -3.2539

Max Act: 3.1553. Min Act: -0.0000

Data Index: 497292 (The Pile)

Max Activating Token Index: 236

Text #2

Max Range: 3.2539. Min Range: -3.2539

Max Act: 1.8074. Min Act: -0.0000

Data Index: 1726298 (The Pile)

Max Activating Token Index: 763

Text #3

Max Range: 3.2539. Min Range: -3.2539

Max Act: 1.9444. Min Act: -0.0000

Data Index: 107228 (The Pile)

Max Activating Token Index: 210

Text #4

Max Range: 3.2539. Min Range: -3.2539

Max Act: 1.6989. Min Act: -0.0000

Data Index: 1735940 (The Pile)

Max Activating Token Index: 435

Text #5

Max Range: 3.2539. Min Range: -3.2539

Max Act: 1.9015. Min Act: -0.0000

Data Index: 776502 (The Pile)

Max Activating Token Index: 779

Text #6

Max Range: 3.2539. Min Range: -3.2539

Max Act: 1.6381. Min Act: -0.0000

Data Index: 1912781 (The Pile)

Max Activating Token Index: 297

Text #7

Max Range: 3.2539. Min Range: -3.2539

Max Act: 1.4880. Min Act: -0.0000

Data Index: 1788762 (The Pile)

Max Activating Token Index: 598

Text #8

Max Range: 3.2539. Min Range: -3.2539

Max Act: 1.7349. Min Act: -0.0000

Data Index: 400304 (The Pile)

Max Activating Token Index: 161

Text #9

Max Range: 3.2539. Min Range: -3.2539

Max Act: 1.5919. Min Act: -0.0000

Data Index: 217600 (The Pile)

Max Activating Token Index: 381

Text #10

Max Range: 3.2539. Min Range: -3.2539

Max Act: 1.5684. Min Act: -0.0000

Data Index: 454230 (The Pile)

Max Activating Token Index: 293

Text #11

Max Range: 3.2539. Min Range: -3.2539

Max Act: 1.5742. Min Act: -0.0000

Data Index: 173599 (The Pile)

Max Activating Token Index: 552

Text #12

Max Range: 3.2539. Min Range: -3.2539

Max Act: 1.5317. Min Act: -0.0000

Data Index: 1525929 (The Pile)

Max Activating Token Index: 1017

Text #13

Max Range: 3.2539. Min Range: -3.2539

Max Act: 1.4645. Min Act: -0.0000

Data Index: 1177574 (The Pile)

Max Activating Token Index: 768

Text #14

Max Range: 3.2539. Min Range: -3.2539

Max Act: 1.3610. Min Act: -0.0000

Data Index: 86062 (The Pile)

Max Activating Token Index: 454

Text #15

Max Range: 3.2539. Min Range: -3.2539

Max Act: 1.4852. Min Act: -0.0000

Data Index: 1623970 (The Pile)

Max Activating Token Index: 338

Text #16

Max Range: 3.2539. Min Range: -3.2539

Max Act: 1.4768. Min Act: -0.0000

Data Index: 1277347 (The Pile)

Max Activating Token Index: 381

Text #17

Max Range: 3.2539. Min Range: -3.2539

Max Act: 1.3744. Min Act: -0.0000

Data Index: 1609882 (The Pile)

Max Activating Token Index: 596

Text #18

Max Range: 3.2539. Min Range: -3.2539

Max Act: 1.9613. Min Act: -0.0000

Data Index: 1891169 (The Pile)

Max Activating Token Index: 187

Text #19

Max Range: 3.2539. Min Range: -3.2539

Max Act: 1.4284. Min Act: -0.0000

Data Index: 525038 (The Pile)

Max Activating Token Index: 896