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

Dataset: The Pile

Neuron 4767 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1922. Min Range: -3.1922

Max Act: 3.1922. Min Act: -0.0000

Data Index: 1851372 (The Pile)

Max Activating Token Index: 339

Text #1

Max Range: 3.1922. Min Range: -3.1922

Max Act: 3.1839. Min Act: -0.0000

Data Index: 1153658 (The Pile)

Max Activating Token Index: 289

Text #2

Max Range: 3.1922. Min Range: -3.1922

Max Act: 3.0296. Min Act: -0.0000

Data Index: 1373885 (The Pile)

Max Activating Token Index: 142

Text #3

Max Range: 3.1922. Min Range: -3.1922

Max Act: 3.1761. Min Act: -0.0000

Data Index: 473270 (The Pile)

Max Activating Token Index: 337

Text #4

Max Range: 3.1922. Min Range: -3.1922

Max Act: 3.1472. Min Act: -0.0000

Data Index: 1911579 (The Pile)

Max Activating Token Index: 473

Text #5

Max Range: 3.1922. Min Range: -3.1922

Max Act: 3.0664. Min Act: -0.0000

Data Index: 605707 (The Pile)

Max Activating Token Index: 70

Text #6

Max Range: 3.1922. Min Range: -3.1922

Max Act: 3.0493. Min Act: -0.0000

Data Index: 620530 (The Pile)

Max Activating Token Index: 588

Text #7

Max Range: 3.1922. Min Range: -3.1922

Max Act: 3.0406. Min Act: -0.0000

Data Index: 1295529 (The Pile)

Max Activating Token Index: 155

Text #8

Max Range: 3.1922. Min Range: -3.1922

Max Act: 3.0264. Min Act: -0.0000

Data Index: 140333 (The Pile)

Max Activating Token Index: 470

Text #9

Max Range: 3.1922. Min Range: -3.1922

Max Act: 3.0191. Min Act: -0.0000

Data Index: 869787 (The Pile)

Max Activating Token Index: 645

Text #10

Max Range: 3.1922. Min Range: -3.1922

Max Act: 3.0072. Min Act: -0.0000

Data Index: 1873525 (The Pile)

Max Activating Token Index: 262

Text #11

Max Range: 3.1922. Min Range: -3.1922

Max Act: 2.8604. Min Act: -0.0000

Data Index: 888592 (The Pile)

Max Activating Token Index: 669

Text #12

Max Range: 3.1922. Min Range: -3.1922

Max Act: 3.0023. Min Act: -0.0000

Data Index: 1787523 (The Pile)

Max Activating Token Index: 355

Text #13

Max Range: 3.1922. Min Range: -3.1922

Max Act: 3.0113. Min Act: -0.0000

Data Index: 629288 (The Pile)

Max Activating Token Index: 927

Text #14

Max Range: 3.1922. Min Range: -3.1922

Max Act: 2.8523. Min Act: -0.0000

Data Index: 1854827 (The Pile)

Max Activating Token Index: 442

Text #15

Max Range: 3.1922. Min Range: -3.1922

Max Act: 2.8570. Min Act: -0.0001

Data Index: 699675 (The Pile)

Max Activating Token Index: 239

Text #16

Max Range: 3.1922. Min Range: -3.1922

Max Act: 2.9941. Min Act: -0.0000

Data Index: 822655 (The Pile)

Max Activating Token Index: 93

Text #17

Max Range: 3.1922. Min Range: -3.1922

Max Act: 2.8435. Min Act: -0.0000

Data Index: 483871 (The Pile)

Max Activating Token Index: 742

Text #18

Max Range: 3.1922. Min Range: -3.1922

Max Act: 2.9737. Min Act: -0.0000

Data Index: 949885 (The Pile)

Max Activating Token Index: 713

Text #19

Max Range: 3.1922. Min Range: -3.1922

Max Act: 2.9639. Min Act: -0.0000

Data Index: 1309258 (The Pile)

Max Activating Token Index: 625