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

Dataset: The Pile

Neuron 4452 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: 0.8639. Min Range: -0.8639

Max Act: 0.8639. Min Act: -0.0000

Data Index: 1429690 (The Pile)

Max Activating Token Index: 786

Text #1

Max Range: 0.8639. Min Range: -0.8639

Max Act: 0.6982. Min Act: -0.0000

Data Index: 498240 (The Pile)

Max Activating Token Index: 757

Text #2

Max Range: 0.8639. Min Range: -0.8639

Max Act: 0.7037. Min Act: -0.0000

Data Index: 1307806 (The Pile)

Max Activating Token Index: 374

Text #3

Max Range: 0.8639. Min Range: -0.8639

Max Act: 0.6777. Min Act: -0.0000

Data Index: 1857839 (The Pile)

Max Activating Token Index: 543

Text #4

Max Range: 0.8639. Min Range: -0.8639

Max Act: 0.6285. Min Act: -0.0000

Data Index: 1406359 (The Pile)

Max Activating Token Index: 765

Text #5

Max Range: 0.8639. Min Range: -0.8639

Max Act: 0.6099. Min Act: -0.0000

Data Index: 1422001 (The Pile)

Max Activating Token Index: 151

Text #6

Max Range: 0.8639. Min Range: -0.8639

Max Act: 0.6665. Min Act: -0.0000

Data Index: 953565 (The Pile)

Max Activating Token Index: 322

Text #7

Max Range: 0.8639. Min Range: -0.8639

Max Act: 0.6254. Min Act: -0.0000

Data Index: 1135359 (The Pile)

Max Activating Token Index: 115

Text #8

Max Range: 0.8639. Min Range: -0.8639

Max Act: 0.6560. Min Act: -0.0000

Data Index: 1836367 (The Pile)

Max Activating Token Index: 222

Text #9

Max Range: 0.8639. Min Range: -0.8639

Max Act: 0.6309. Min Act: -0.0000

Data Index: 1294032 (The Pile)

Max Activating Token Index: 679

Text #10

Max Range: 0.8639. Min Range: -0.8639

Max Act: 0.6295. Min Act: -0.0000

Data Index: 1774730 (The Pile)

Max Activating Token Index: 657

Text #11

Max Range: 0.8639. Min Range: -0.8639

Max Act: 0.6365. Min Act: -0.0000

Data Index: 785212 (The Pile)

Max Activating Token Index: 49

Text #12

Max Range: 0.8639. Min Range: -0.8639

Max Act: 0.6257. Min Act: -0.0000

Data Index: 643870 (The Pile)

Max Activating Token Index: 284

Text #13

Max Range: 0.8639. Min Range: -0.8639

Max Act: 0.5661. Min Act: -0.0000

Data Index: 1307854 (The Pile)

Max Activating Token Index: 105

Text #14

Max Range: 0.8639. Min Range: -0.8639

Max Act: 0.6011. Min Act: -0.0000

Data Index: 1820960 (The Pile)

Max Activating Token Index: 500

Text #15

Max Range: 0.8639. Min Range: -0.8639

Max Act: 0.6026. Min Act: -0.0000

Data Index: 898912 (The Pile)

Max Activating Token Index: 121

Text #16

Max Range: 0.8639. Min Range: -0.8639

Max Act: 0.5852. Min Act: -0.0000

Data Index: 1337644 (The Pile)

Max Activating Token Index: 550

Text #17

Max Range: 0.8639. Min Range: -0.8639

Max Act: 0.6009. Min Act: -0.0000

Data Index: 396256 (The Pile)

Max Activating Token Index: 358

Text #18

Max Range: 0.8639. Min Range: -0.8639

Max Act: 0.6174. Min Act: -0.0000

Data Index: 913118 (The Pile)

Max Activating Token Index: 367

Text #19

Max Range: 0.8639. Min Range: -0.8639

Max Act: 0.5864. Min Act: -0.0000

Data Index: 1881933 (The Pile)

Max Activating Token Index: 530