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

Dataset: The Pile

Neuron 2043 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: 0.5906. Min Range: -0.5906

Max Act: 0.5906. Min Act: -0.0000

Data Index: 1371510 (The Pile)

Max Activating Token Index: 1018

Text #1

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.5131. Min Act: -0.0000

Data Index: 646090 (The Pile)

Max Activating Token Index: 972

Text #2

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.4467. Min Act: -0.0000

Data Index: 1528639 (The Pile)

Max Activating Token Index: 500

Text #3

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.4203. Min Act: -0.0000

Data Index: 530227 (The Pile)

Max Activating Token Index: 801

Text #4

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.4320. Min Act: -0.0000

Data Index: 1404959 (The Pile)

Max Activating Token Index: 334

Text #5

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.4155. Min Act: -0.0000

Data Index: 1863363 (The Pile)

Max Activating Token Index: 420

Text #6

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.4227. Min Act: -0.0000

Data Index: 807181 (The Pile)

Max Activating Token Index: 934

Text #7

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.4100. Min Act: 0.0001

Data Index: 1490972 (The Pile)

Max Activating Token Index: 541

Text #8

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.4223. Min Act: -0.0000

Data Index: 144292 (The Pile)

Max Activating Token Index: 54

Text #9

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.3909. Min Act: -0.0000

Data Index: 732491 (The Pile)

Max Activating Token Index: 584

Text #10

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.3817. Min Act: 0.0000

Data Index: 964887 (The Pile)

Max Activating Token Index: 998

Text #11

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.3843. Min Act: -0.0000

Data Index: 663037 (The Pile)

Max Activating Token Index: 348

Text #12

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.3783. Min Act: -0.0000

Data Index: 219024 (The Pile)

Max Activating Token Index: 259

Text #13

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.3713. Min Act: 0.0000

Data Index: 1981263 (The Pile)

Max Activating Token Index: 405

Text #14

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.3963. Min Act: -0.0000

Data Index: 1193710 (The Pile)

Max Activating Token Index: 836

Text #15

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.3411. Min Act: 0.0000

Data Index: 1080000 (The Pile)

Max Activating Token Index: 784

Text #16

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.3804. Min Act: -0.0000

Data Index: 986991 (The Pile)

Max Activating Token Index: 720

Text #17

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.3574. Min Act: -0.0000

Data Index: 1744786 (The Pile)

Max Activating Token Index: 385

Text #18

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.3324. Min Act: -0.0000

Data Index: 1570703 (The Pile)

Max Activating Token Index: 891

Text #19

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.3209. Min Act: -0.0000

Data Index: 326603 (The Pile)

Max Activating Token Index: 521