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

Dataset: The Pile

Neuron 5063 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: 5.1436. Min Range: -5.1436

Max Act: 5.1436. Min Act: -0.0000

Data Index: 1112423 (The Pile)

Max Activating Token Index: 385

Text #1

Max Range: 5.1436. Min Range: -5.1436

Max Act: 4.6126. Min Act: -0.0000

Data Index: 849727 (The Pile)

Max Activating Token Index: 441

Text #2

Max Range: 5.1436. Min Range: -5.1436

Max Act: 4.3411. Min Act: -0.0000

Data Index: 1875683 (The Pile)

Max Activating Token Index: 402

Text #3

Max Range: 5.1436. Min Range: -5.1436

Max Act: 3.7602. Min Act: -0.0000

Data Index: 1719565 (The Pile)

Max Activating Token Index: 753

Text #4

Max Range: 5.1436. Min Range: -5.1436

Max Act: 3.7074. Min Act: -0.0000

Data Index: 1214046 (The Pile)

Max Activating Token Index: 934

Text #5

Max Range: 5.1436. Min Range: -5.1436

Max Act: 4.0608. Min Act: -0.0000

Data Index: 1936747 (The Pile)

Max Activating Token Index: 980

Text #6

Max Range: 5.1436. Min Range: -5.1436

Max Act: 3.2613. Min Act: -0.0000

Data Index: 1144263 (The Pile)

Max Activating Token Index: 926

Text #7

Max Range: 5.1436. Min Range: -5.1436

Max Act: 3.5739. Min Act: -0.0000

Data Index: 329107 (The Pile)

Max Activating Token Index: 449

Text #8

Max Range: 5.1436. Min Range: -5.1436

Max Act: 3.7275. Min Act: -0.0000

Data Index: 416011 (The Pile)

Max Activating Token Index: 120

Text #9

Max Range: 5.1436. Min Range: -5.1436

Max Act: 3.4756. Min Act: -0.0000

Data Index: 511339 (The Pile)

Max Activating Token Index: 155

Text #10

Max Range: 5.1436. Min Range: -5.1436

Max Act: 3.6997. Min Act: -0.0000

Data Index: 1082519 (The Pile)

Max Activating Token Index: 704

Text #11

Max Range: 5.1436. Min Range: -5.1436

Max Act: 3.9109. Min Act: -0.0000

Data Index: 293913 (The Pile)

Max Activating Token Index: 549

Text #12

Max Range: 5.1436. Min Range: -5.1436

Max Act: 3.9011. Min Act: -0.0000

Data Index: 1894140 (The Pile)

Max Activating Token Index: 770

Text #13

Max Range: 5.1436. Min Range: -5.1436

Max Act: 3.5247. Min Act: -0.0000

Data Index: 672159 (The Pile)

Max Activating Token Index: 704

Text #14

Max Range: 5.1436. Min Range: -5.1436

Max Act: 3.3483. Min Act: -0.0000

Data Index: 1915230 (The Pile)

Max Activating Token Index: 76

Text #15

Max Range: 5.1436. Min Range: -5.1436

Max Act: 3.2914. Min Act: -0.0000

Data Index: 1347148 (The Pile)

Max Activating Token Index: 368

Text #16

Max Range: 5.1436. Min Range: -5.1436

Max Act: 3.4723. Min Act: -0.0000

Data Index: 595014 (The Pile)

Max Activating Token Index: 472

Text #17

Max Range: 5.1436. Min Range: -5.1436

Max Act: 3.2420. Min Act: -0.0000

Data Index: 1324530 (The Pile)

Max Activating Token Index: 829

Text #18

Max Range: 5.1436. Min Range: -5.1436

Max Act: 3.2228. Min Act: -0.0000

Data Index: 1817449 (The Pile)

Max Activating Token Index: 80

Text #19

Max Range: 5.1436. Min Range: -5.1436

Max Act: 3.3761. Min Act: -0.0000

Data Index: 29335 (The Pile)

Max Activating Token Index: 347