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

Dataset: The Pile

Neuron 4196 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: 1.5574. Min Range: -1.5574

Max Act: 1.5574. Min Act: -0.0000

Data Index: 1314175 (The Pile)

Max Activating Token Index: 16

Text #1

Max Range: 1.5574. Min Range: -1.5574

Max Act: 1.3149. Min Act: -0.0000

Data Index: 1656561 (The Pile)

Max Activating Token Index: 15

Text #2

Max Range: 1.5574. Min Range: -1.5574

Max Act: 1.2397. Min Act: -0.0000

Data Index: 320305 (The Pile)

Max Activating Token Index: 458

Text #3

Max Range: 1.5574. Min Range: -1.5574

Max Act: 1.1731. Min Act: -0.0000

Data Index: 1439734 (The Pile)

Max Activating Token Index: 442

Text #4

Max Range: 1.5574. Min Range: -1.5574

Max Act: 1.0420. Min Act: -0.0000

Data Index: 290673 (The Pile)

Max Activating Token Index: 22

Text #5

Max Range: 1.5574. Min Range: -1.5574

Max Act: 1.1270. Min Act: -0.0000

Data Index: 748938 (The Pile)

Max Activating Token Index: 615

Text #6

Max Range: 1.5574. Min Range: -1.5574

Max Act: 0.9762. Min Act: -0.0000

Data Index: 1518707 (The Pile)

Max Activating Token Index: 24

Text #7

Max Range: 1.5574. Min Range: -1.5574

Max Act: 1.0688. Min Act: -0.0000

Data Index: 892436 (The Pile)

Max Activating Token Index: 1002

Text #8

Max Range: 1.5574. Min Range: -1.5574

Max Act: 0.9570. Min Act: -0.0000

Data Index: 1012368 (The Pile)

Max Activating Token Index: 387

Text #9

Max Range: 1.5574. Min Range: -1.5574

Max Act: 1.0536. Min Act: -0.0000

Data Index: 753634 (The Pile)

Max Activating Token Index: 910

Text #10

Max Range: 1.5574. Min Range: -1.5574

Max Act: 1.0025. Min Act: -0.0000

Data Index: 1802063 (The Pile)

Max Activating Token Index: 20

Text #11

Max Range: 1.5574. Min Range: -1.5574

Max Act: 1.0094. Min Act: -0.0000

Data Index: 984827 (The Pile)

Max Activating Token Index: 20

Text #12

Max Range: 1.5574. Min Range: -1.5574

Max Act: 0.9803. Min Act: -0.0000

Data Index: 1611728 (The Pile)

Max Activating Token Index: 860

Text #13

Max Range: 1.5574. Min Range: -1.5574

Max Act: 0.9457. Min Act: -0.0000

Data Index: 419067 (The Pile)

Max Activating Token Index: 280

Text #14

Max Range: 1.5574. Min Range: -1.5574

Max Act: 0.9405. Min Act: -0.0000

Data Index: 425378 (The Pile)

Max Activating Token Index: 276

Text #15

Max Range: 1.5574. Min Range: -1.5574

Max Act: 0.8622. Min Act: -0.0000

Data Index: 1226665 (The Pile)

Max Activating Token Index: 882

Text #16

Max Range: 1.5574. Min Range: -1.5574

Max Act: 0.9428. Min Act: -0.0000

Data Index: 854985 (The Pile)

Max Activating Token Index: 330

Text #17

Max Range: 1.5574. Min Range: -1.5574

Max Act: 0.9141. Min Act: -0.0000

Data Index: 299900 (The Pile)

Max Activating Token Index: 544

Text #18

Max Range: 1.5574. Min Range: -1.5574

Max Act: 0.9578. Min Act: -0.0000

Data Index: 465058 (The Pile)

Max Activating Token Index: 801

Text #19

Max Range: 1.5574. Min Range: -1.5574

Max Act: 1.0187. Min Act: -0.0000

Data Index: 864367 (The Pile)

Max Activating Token Index: 795