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

Dataset: The Pile

Neuron 3140 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1821. Min Range: -1.1821

Max Act: 1.1821. Min Act: -0.0000

Data Index: 1724013 (The Pile)

Max Activating Token Index: 554

Text #1

Max Range: 1.1821. Min Range: -1.1821

Max Act: 1.0434. Min Act: -0.0000

Data Index: 1005402 (The Pile)

Max Activating Token Index: 461

Text #2

Max Range: 1.1821. Min Range: -1.1821

Max Act: 1.0423. Min Act: -0.0000

Data Index: 1866433 (The Pile)

Max Activating Token Index: 310

Text #3

Max Range: 1.1821. Min Range: -1.1821

Max Act: 1.0020. Min Act: -0.0000

Data Index: 1298905 (The Pile)

Max Activating Token Index: 1017

Text #4

Max Range: 1.1821. Min Range: -1.1821

Max Act: 1.0672. Min Act: -0.0000

Data Index: 1252509 (The Pile)

Max Activating Token Index: 167

Text #5

Max Range: 1.1821. Min Range: -1.1821

Max Act: 0.9355. Min Act: -0.0000

Data Index: 1565769 (The Pile)

Max Activating Token Index: 230

Text #6

Max Range: 1.1821. Min Range: -1.1821

Max Act: 0.9487. Min Act: -0.0000

Data Index: 1056570 (The Pile)

Max Activating Token Index: 308

Text #7

Max Range: 1.1821. Min Range: -1.1821

Max Act: 1.0074. Min Act: -0.0000

Data Index: 1964222 (The Pile)

Max Activating Token Index: 419

Text #8

Max Range: 1.1821. Min Range: -1.1821

Max Act: 0.9811. Min Act: -0.0000

Data Index: 1503171 (The Pile)

Max Activating Token Index: 502

Text #9

Max Range: 1.1821. Min Range: -1.1821

Max Act: 0.9662. Min Act: -0.0000

Data Index: 282023 (The Pile)

Max Activating Token Index: 120

Text #10

Max Range: 1.1821. Min Range: -1.1821

Max Act: 0.9332. Min Act: -0.0000

Data Index: 1450605 (The Pile)

Max Activating Token Index: 904

Text #11

Max Range: 1.1821. Min Range: -1.1821

Max Act: 0.9500. Min Act: -0.0000

Data Index: 1176904 (The Pile)

Max Activating Token Index: 735

Text #12

Max Range: 1.1821. Min Range: -1.1821

Max Act: 0.9831. Min Act: -0.0000

Data Index: 1524774 (The Pile)

Max Activating Token Index: 669

Text #13

Max Range: 1.1821. Min Range: -1.1821

Max Act: 0.9421. Min Act: -0.0000

Data Index: 1929455 (The Pile)

Max Activating Token Index: 1003

Text #14

Max Range: 1.1821. Min Range: -1.1821

Max Act: 0.9743. Min Act: -0.0000

Data Index: 12619 (The Pile)

Max Activating Token Index: 570

Text #15

Max Range: 1.1821. Min Range: -1.1821

Max Act: 0.9914. Min Act: -0.0000

Data Index: 1296813 (The Pile)

Max Activating Token Index: 887

Text #16

Max Range: 1.1821. Min Range: -1.1821

Max Act: 0.9318. Min Act: -0.0000

Data Index: 899773 (The Pile)

Max Activating Token Index: 345

Text #17

Max Range: 1.1821. Min Range: -1.1821

Max Act: 0.8467. Min Act: -0.0000

Data Index: 1672412 (The Pile)

Max Activating Token Index: 171

Text #18

Max Range: 1.1821. Min Range: -1.1821

Max Act: 0.9251. Min Act: -0.0000

Data Index: 1474398 (The Pile)

Max Activating Token Index: 390

Text #19

Max Range: 1.1821. Min Range: -1.1821

Max Act: 0.9001. Min Act: -0.0000

Data Index: 63221 (The Pile)

Max Activating Token Index: 137