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

Dataset: The Pile

Neuron 1838 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.7624. Min Range: -3.7624

Max Act: 3.7624. Min Act: -0.0000

Data Index: 1917698 (The Pile)

Max Activating Token Index: 153

Text #1

Max Range: 3.7624. Min Range: -3.7624

Max Act: 3.4640. Min Act: -0.0000

Data Index: 372819 (The Pile)

Max Activating Token Index: 185

Text #2

Max Range: 3.7624. Min Range: -3.7624

Max Act: 3.5527. Min Act: -0.0000

Data Index: 1886228 (The Pile)

Max Activating Token Index: 505

Text #3

Max Range: 3.7624. Min Range: -3.7624

Max Act: 3.6208. Min Act: -0.0000

Data Index: 449140 (The Pile)

Max Activating Token Index: 492

Text #4

Max Range: 3.7624. Min Range: -3.7624

Max Act: 3.3521. Min Act: -0.0000

Data Index: 824479 (The Pile)

Max Activating Token Index: 217

Text #5

Max Range: 3.7624. Min Range: -3.7624

Max Act: 3.2713. Min Act: -0.0000

Data Index: 258186 (The Pile)

Max Activating Token Index: 559

Text #6

Max Range: 3.7624. Min Range: -3.7624

Max Act: 3.0386. Min Act: -0.0000

Data Index: 495568 (The Pile)

Max Activating Token Index: 123

Text #7

Max Range: 3.7624. Min Range: -3.7624

Max Act: 3.1696. Min Act: -0.0000

Data Index: 1720333 (The Pile)

Max Activating Token Index: 38

Text #8

Max Range: 3.7624. Min Range: -3.7624

Max Act: 3.1342. Min Act: -0.0000

Data Index: 1249646 (The Pile)

Max Activating Token Index: 319

Text #9

Max Range: 3.7624. Min Range: -3.7624

Max Act: 3.1286. Min Act: -0.0000

Data Index: 430744 (The Pile)

Max Activating Token Index: 490

Text #10

Max Range: 3.7624. Min Range: -3.7624

Max Act: 2.9640. Min Act: -0.0000

Data Index: 484870 (The Pile)

Max Activating Token Index: 312

Text #11

Max Range: 3.7624. Min Range: -3.7624

Max Act: 3.0376. Min Act: -0.0000

Data Index: 953644 (The Pile)

Max Activating Token Index: 254

Text #12

Max Range: 3.7624. Min Range: -3.7624

Max Act: 3.0246. Min Act: -0.0000

Data Index: 1425225 (The Pile)

Max Activating Token Index: 507

Text #13

Max Range: 3.7624. Min Range: -3.7624

Max Act: 3.0347. Min Act: -0.0000

Data Index: 1215245 (The Pile)

Max Activating Token Index: 210

Text #14

Max Range: 3.7624. Min Range: -3.7624

Max Act: 2.8510. Min Act: -0.0000

Data Index: 1930464 (The Pile)

Max Activating Token Index: 940

Text #15

Max Range: 3.7624. Min Range: -3.7624

Max Act: 2.9693. Min Act: -0.0000

Data Index: 1945866 (The Pile)

Max Activating Token Index: 230

Text #16

Max Range: 3.7624. Min Range: -3.7624

Max Act: 2.9097. Min Act: -0.0000

Data Index: 350896 (The Pile)

Max Activating Token Index: 465

Text #17

Max Range: 3.7624. Min Range: -3.7624

Max Act: 2.9017. Min Act: -0.0000

Data Index: 951122 (The Pile)

Max Activating Token Index: 174

Text #18

Max Range: 3.7624. Min Range: -3.7624

Max Act: 2.9971. Min Act: -0.0000

Data Index: 482058 (The Pile)

Max Activating Token Index: 673

Text #19

Max Range: 3.7624. Min Range: -3.7624

Max Act: 2.9828. Min Act: -0.0000

Data Index: 1781868 (The Pile)

Max Activating Token Index: 895