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

Dataset: The Pile

Neuron 2582 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: 0.9640. Min Range: -0.9640

Max Act: 0.9451. Min Act: -0.0000

Data Index: 1437711 (The Pile)

Max Activating Token Index: 765

Text #1

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.9600. Min Act: -0.0000

Data Index: 1636019 (The Pile)

Max Activating Token Index: 217

Text #2

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.9640. Min Act: -0.0000

Data Index: 429812 (The Pile)

Max Activating Token Index: 66

Text #3

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.8604. Min Act: -0.0000

Data Index: 832262 (The Pile)

Max Activating Token Index: 480

Text #4

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.7666. Min Act: -0.0000

Data Index: 1587009 (The Pile)

Max Activating Token Index: 882

Text #5

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.6202. Min Act: -0.0000

Data Index: 135291 (The Pile)

Max Activating Token Index: 985

Text #6

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.6346. Min Act: -0.0000

Data Index: 1431469 (The Pile)

Max Activating Token Index: 469

Text #7

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.6533. Min Act: -0.0000

Data Index: 1866211 (The Pile)

Max Activating Token Index: 743

Text #8

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.6540. Min Act: -0.0000

Data Index: 297818 (The Pile)

Max Activating Token Index: 553

Text #9

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.6257. Min Act: -0.0000

Data Index: 1655959 (The Pile)

Max Activating Token Index: 708

Text #10

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.6330. Min Act: -0.0000

Data Index: 735166 (The Pile)

Max Activating Token Index: 426

Text #11

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.6222. Min Act: -0.0000

Data Index: 1086337 (The Pile)

Max Activating Token Index: 520

Text #12

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.6366. Min Act: -0.0000

Data Index: 1091510 (The Pile)

Max Activating Token Index: 439

Text #13

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.6022. Min Act: -0.0000

Data Index: 1822880 (The Pile)

Max Activating Token Index: 290

Text #14

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.6024. Min Act: -0.0000

Data Index: 1244497 (The Pile)

Max Activating Token Index: 126

Text #15

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.6328. Min Act: -0.0000

Data Index: 628417 (The Pile)

Max Activating Token Index: 29

Text #16

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.6741. Min Act: -0.0000

Data Index: 34740 (The Pile)

Max Activating Token Index: 804

Text #17

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.6323. Min Act: -0.0000

Data Index: 1317270 (The Pile)

Max Activating Token Index: 545

Text #18

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.5559. Min Act: -0.0000

Data Index: 522323 (The Pile)

Max Activating Token Index: 811

Text #19

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.6706. Min Act: -0.0000

Data Index: 65881 (The Pile)

Max Activating Token Index: 980