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

Dataset: The Pile

Neuron 4430 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2384. Min Range: -1.2384

Max Act: 1.1803. Min Act: -0.0000

Data Index: 1714480 (The Pile)

Max Activating Token Index: 953

Text #1

Max Range: 1.2384. Min Range: -1.2384

Max Act: 1.2384. Min Act: -0.0000

Data Index: 335492 (The Pile)

Max Activating Token Index: 271

Text #2

Max Range: 1.2384. Min Range: -1.2384

Max Act: 1.1575. Min Act: -0.0000

Data Index: 1211733 (The Pile)

Max Activating Token Index: 111

Text #3

Max Range: 1.2384. Min Range: -1.2384

Max Act: 1.1466. Min Act: -0.0000

Data Index: 1247342 (The Pile)

Max Activating Token Index: 974

Text #4

Max Range: 1.2384. Min Range: -1.2384

Max Act: 1.2067. Min Act: -0.0000

Data Index: 242010 (The Pile)

Max Activating Token Index: 66

Text #5

Max Range: 1.2384. Min Range: -1.2384

Max Act: 1.1430. Min Act: -0.0000

Data Index: 575707 (The Pile)

Max Activating Token Index: 519

Text #6

Max Range: 1.2384. Min Range: -1.2384

Max Act: 1.1986. Min Act: -0.0000

Data Index: 42701 (The Pile)

Max Activating Token Index: 299

Text #7

Max Range: 1.2384. Min Range: -1.2384

Max Act: 1.1591. Min Act: -0.0000

Data Index: 321360 (The Pile)

Max Activating Token Index: 309

Text #8

Max Range: 1.2384. Min Range: -1.2384

Max Act: 1.0995. Min Act: -0.0000

Data Index: 238202 (The Pile)

Max Activating Token Index: 83

Text #9

Max Range: 1.2384. Min Range: -1.2384

Max Act: 1.1206. Min Act: -0.0000

Data Index: 116321 (The Pile)

Max Activating Token Index: 369

Text #10

Max Range: 1.2384. Min Range: -1.2384

Max Act: 1.2043. Min Act: -0.0000

Data Index: 1900425 (The Pile)

Max Activating Token Index: 158

Text #11

Max Range: 1.2384. Min Range: -1.2384

Max Act: 1.0580. Min Act: -0.0000

Data Index: 1450472 (The Pile)

Max Activating Token Index: 647

Text #12

Max Range: 1.2384. Min Range: -1.2384

Max Act: 1.0986. Min Act: -0.0000

Data Index: 763335 (The Pile)

Max Activating Token Index: 80

Text #13

Max Range: 1.2384. Min Range: -1.2384

Max Act: 1.0157. Min Act: -0.0000

Data Index: 943599 (The Pile)

Max Activating Token Index: 349

Text #14

Max Range: 1.2384. Min Range: -1.2384

Max Act: 1.0650. Min Act: -0.0000

Data Index: 71561 (The Pile)

Max Activating Token Index: 729

Text #15

Max Range: 1.2384. Min Range: -1.2384

Max Act: 1.0736. Min Act: -0.0000

Data Index: 208821 (The Pile)

Max Activating Token Index: 303

Text #16

Max Range: 1.2384. Min Range: -1.2384

Max Act: 1.0262. Min Act: -0.0000

Data Index: 819066 (The Pile)

Max Activating Token Index: 493

Text #17

Max Range: 1.2384. Min Range: -1.2384

Max Act: 1.1228. Min Act: -0.0000

Data Index: 1315656 (The Pile)

Max Activating Token Index: 312

Text #18

Max Range: 1.2384. Min Range: -1.2384

Max Act: 1.0632. Min Act: -0.0000

Data Index: 1079708 (The Pile)

Max Activating Token Index: 889

Text #19

Max Range: 1.2384. Min Range: -1.2384

Max Act: 1.0482. Min Act: -0.0000

Data Index: 360440 (The Pile)

Max Activating Token Index: 271