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

Dataset: The Pile

Neuron 3388 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: 1.2218. Min Range: -1.2218

Max Act: 1.2218. Min Act: -0.0000

Data Index: 1894239 (The Pile)

Max Activating Token Index: 1014

Text #1

Max Range: 1.2218. Min Range: -1.2218

Max Act: 1.1761. Min Act: -0.0000

Data Index: 338198 (The Pile)

Max Activating Token Index: 880

Text #2

Max Range: 1.2218. Min Range: -1.2218

Max Act: 1.1749. Min Act: -0.0000

Data Index: 1870184 (The Pile)

Max Activating Token Index: 945

Text #3

Max Range: 1.2218. Min Range: -1.2218

Max Act: 1.1408. Min Act: -0.0000

Data Index: 651003 (The Pile)

Max Activating Token Index: 879

Text #4

Max Range: 1.2218. Min Range: -1.2218

Max Act: 1.1609. Min Act: -0.0000

Data Index: 58351 (The Pile)

Max Activating Token Index: 996

Text #5

Max Range: 1.2218. Min Range: -1.2218

Max Act: 1.1522. Min Act: -0.0000

Data Index: 698970 (The Pile)

Max Activating Token Index: 873

Text #6

Max Range: 1.2218. Min Range: -1.2218

Max Act: 1.1217. Min Act: -0.0000

Data Index: 609794 (The Pile)

Max Activating Token Index: 906

Text #7

Max Range: 1.2218. Min Range: -1.2218

Max Act: 1.1519. Min Act: -0.0000

Data Index: 376764 (The Pile)

Max Activating Token Index: 939

Text #8

Max Range: 1.2218. Min Range: -1.2218

Max Act: 1.1462. Min Act: -0.0000

Data Index: 1997229 (The Pile)

Max Activating Token Index: 674

Text #9

Max Range: 1.2218. Min Range: -1.2218

Max Act: 1.0424. Min Act: -0.0000

Data Index: 303863 (The Pile)

Max Activating Token Index: 639

Text #10

Max Range: 1.2218. Min Range: -1.2218

Max Act: 1.1231. Min Act: -0.0000

Data Index: 353735 (The Pile)

Max Activating Token Index: 832

Text #11

Max Range: 1.2218. Min Range: -1.2218

Max Act: 1.0715. Min Act: -0.0000

Data Index: 173717 (The Pile)

Max Activating Token Index: 934

Text #12

Max Range: 1.2218. Min Range: -1.2218

Max Act: 1.0225. Min Act: -0.0000

Data Index: 954825 (The Pile)

Max Activating Token Index: 553

Text #13

Max Range: 1.2218. Min Range: -1.2218

Max Act: 1.0678. Min Act: -0.0000

Data Index: 547385 (The Pile)

Max Activating Token Index: 468

Text #14

Max Range: 1.2218. Min Range: -1.2218

Max Act: 1.1248. Min Act: -0.0000

Data Index: 1042914 (The Pile)

Max Activating Token Index: 670

Text #15

Max Range: 1.2218. Min Range: -1.2218

Max Act: 1.0922. Min Act: -0.0000

Data Index: 1658745 (The Pile)

Max Activating Token Index: 754

Text #16

Max Range: 1.2218. Min Range: -1.2218

Max Act: 1.1420. Min Act: -0.0000

Data Index: 535583 (The Pile)

Max Activating Token Index: 775

Text #17

Max Range: 1.2218. Min Range: -1.2218

Max Act: 1.0642. Min Act: -0.0000

Data Index: 1725310 (The Pile)

Max Activating Token Index: 784

Text #18

Max Range: 1.2218. Min Range: -1.2218

Max Act: 1.0683. Min Act: -0.0000

Data Index: 1373498 (The Pile)

Max Activating Token Index: 505

Text #19

Max Range: 1.2218. Min Range: -1.2218

Max Act: 1.0777. Min Act: -0.0000

Data Index: 1532974 (The Pile)

Max Activating Token Index: 715