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

Dataset: The Pile

Neuron 999 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1936. Min Range: -3.1936

Max Act: 2.9823. Min Act: -0.0000

Data Index: 1686809 (The Pile)

Max Activating Token Index: 1014

Text #1

Max Range: 3.1936. Min Range: -3.1936

Max Act: 2.9033. Min Act: -0.0000

Data Index: 1426633 (The Pile)

Max Activating Token Index: 37

Text #2

Max Range: 3.1936. Min Range: -3.1936

Max Act: 3.1936. Min Act: -0.0000

Data Index: 1723698 (The Pile)

Max Activating Token Index: 787

Text #3

Max Range: 3.1936. Min Range: -3.1936

Max Act: 2.9037. Min Act: -0.0000

Data Index: 280909 (The Pile)

Max Activating Token Index: 229

Text #4

Max Range: 3.1936. Min Range: -3.1936

Max Act: 2.7733. Min Act: -0.0000

Data Index: 1839682 (The Pile)

Max Activating Token Index: 117

Text #5

Max Range: 3.1936. Min Range: -3.1936

Max Act: 2.7966. Min Act: -0.0000

Data Index: 1063999 (The Pile)

Max Activating Token Index: 788

Text #6

Max Range: 3.1936. Min Range: -3.1936

Max Act: 2.9511. Min Act: -0.0000

Data Index: 1976429 (The Pile)

Max Activating Token Index: 38

Text #7

Max Range: 3.1936. Min Range: -3.1936

Max Act: 2.4356. Min Act: -0.0001

Data Index: 1983963 (The Pile)

Max Activating Token Index: 151

Text #8

Max Range: 3.1936. Min Range: -3.1936

Max Act: 2.6778. Min Act: -0.0000

Data Index: 423364 (The Pile)

Max Activating Token Index: 303

Text #9

Max Range: 3.1936. Min Range: -3.1936

Max Act: 2.6451. Min Act: -0.0000

Data Index: 1244713 (The Pile)

Max Activating Token Index: 528

Text #10

Max Range: 3.1936. Min Range: -3.1936

Max Act: 2.7979. Min Act: -0.0000

Data Index: 1404524 (The Pile)

Max Activating Token Index: 299

Text #11

Max Range: 3.1936. Min Range: -3.1936

Max Act: 2.5901. Min Act: -0.0000

Data Index: 300355 (The Pile)

Max Activating Token Index: 858

Text #12

Max Range: 3.1936. Min Range: -3.1936

Max Act: 2.6996. Min Act: -0.0001

Data Index: 1610636 (The Pile)

Max Activating Token Index: 598

Text #13

Max Range: 3.1936. Min Range: -3.1936

Max Act: 2.4622. Min Act: -0.0001

Data Index: 871515 (The Pile)

Max Activating Token Index: 183

Text #14

Max Range: 3.1936. Min Range: -3.1936

Max Act: 2.4123. Min Act: -0.0000

Data Index: 1708466 (The Pile)

Max Activating Token Index: 468

Text #15

Max Range: 3.1936. Min Range: -3.1936

Max Act: 2.5607. Min Act: -0.0000

Data Index: 1105002 (The Pile)

Max Activating Token Index: 811

Text #16

Max Range: 3.1936. Min Range: -3.1936

Max Act: 2.6341. Min Act: -0.0000

Data Index: 1478846 (The Pile)

Max Activating Token Index: 922

Text #17

Max Range: 3.1936. Min Range: -3.1936

Max Act: 2.4900. Min Act: -0.0000

Data Index: 54965 (The Pile)

Max Activating Token Index: 419

Text #18

Max Range: 3.1936. Min Range: -3.1936

Max Act: 2.5783. Min Act: -0.0000

Data Index: 1406979 (The Pile)

Max Activating Token Index: 555

Text #19

Max Range: 3.1936. Min Range: -3.1936

Max Act: 2.5802. Min Act: -0.0000

Data Index: 914794 (The Pile)

Max Activating Token Index: 518