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

Dataset: The Pile

Neuron 692 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: 4.7407. Min Range: -4.7407

Max Act: 4.7407. Min Act: -0.0000

Data Index: 1253409 (The Pile)

Max Activating Token Index: 687

Text #1

Max Range: 4.7407. Min Range: -4.7407

Max Act: 4.5940. Min Act: -0.0000

Data Index: 1852436 (The Pile)

Max Activating Token Index: 471

Text #2

Max Range: 4.7407. Min Range: -4.7407

Max Act: 4.1714. Min Act: -0.0000

Data Index: 1484956 (The Pile)

Max Activating Token Index: 400

Text #3

Max Range: 4.7407. Min Range: -4.7407

Max Act: 4.0147. Min Act: -0.0000

Data Index: 1344951 (The Pile)

Max Activating Token Index: 871

Text #4

Max Range: 4.7407. Min Range: -4.7407

Max Act: 4.0486. Min Act: -0.0000

Data Index: 195019 (The Pile)

Max Activating Token Index: 914

Text #5

Max Range: 4.7407. Min Range: -4.7407

Max Act: 3.8733. Min Act: -0.0000

Data Index: 1761553 (The Pile)

Max Activating Token Index: 585

Text #6

Max Range: 4.7407. Min Range: -4.7407

Max Act: 3.8521. Min Act: -0.0000

Data Index: 1750826 (The Pile)

Max Activating Token Index: 865

Text #7

Max Range: 4.7407. Min Range: -4.7407

Max Act: 4.1510. Min Act: -0.0000

Data Index: 1038506 (The Pile)

Max Activating Token Index: 804

Text #8

Max Range: 4.7407. Min Range: -4.7407

Max Act: 3.9030. Min Act: -0.0000

Data Index: 142147 (The Pile)

Max Activating Token Index: 957

Text #9

Max Range: 4.7407. Min Range: -4.7407

Max Act: 3.7100. Min Act: -0.0000

Data Index: 1685982 (The Pile)

Max Activating Token Index: 338

Text #10

Max Range: 4.7407. Min Range: -4.7407

Max Act: 3.6715. Min Act: -0.0000

Data Index: 1317671 (The Pile)

Max Activating Token Index: 630

Text #11

Max Range: 4.7407. Min Range: -4.7407

Max Act: 3.6427. Min Act: -0.0000

Data Index: 462770 (The Pile)

Max Activating Token Index: 580

Text #12

Max Range: 4.7407. Min Range: -4.7407

Max Act: 3.4739. Min Act: -0.0000

Data Index: 1805918 (The Pile)

Max Activating Token Index: 886

Text #13

Max Range: 4.7407. Min Range: -4.7407

Max Act: 3.4503. Min Act: -0.0000

Data Index: 191459 (The Pile)

Max Activating Token Index: 820

Text #14

Max Range: 4.7407. Min Range: -4.7407

Max Act: 3.5139. Min Act: -0.0000

Data Index: 1076334 (The Pile)

Max Activating Token Index: 97

Text #15

Max Range: 4.7407. Min Range: -4.7407

Max Act: 3.4522. Min Act: -0.0000

Data Index: 715678 (The Pile)

Max Activating Token Index: 242

Text #16

Max Range: 4.7407. Min Range: -4.7407

Max Act: 3.2605. Min Act: -0.0000

Data Index: 1334712 (The Pile)

Max Activating Token Index: 828

Text #17

Max Range: 4.7407. Min Range: -4.7407

Max Act: 3.2732. Min Act: -0.0000

Data Index: 1600133 (The Pile)

Max Activating Token Index: 203

Text #18

Max Range: 4.7407. Min Range: -4.7407

Max Act: 3.3936. Min Act: -0.0000

Data Index: 1879141 (The Pile)

Max Activating Token Index: 400

Text #19

Max Range: 4.7407. Min Range: -4.7407

Max Act: 3.3898. Min Act: -0.0000

Data Index: 50818 (The Pile)

Max Activating Token Index: 291