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

Dataset: The Pile

Neuron 2898 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: 1.3496. Min Range: -1.3496

Max Act: 1.3496. Min Act: -0.0000

Data Index: 1073975 (The Pile)

Max Activating Token Index: 958

Text #1

Max Range: 1.3496. Min Range: -1.3496

Max Act: 1.1939. Min Act: -0.0000

Data Index: 1454066 (The Pile)

Max Activating Token Index: 559

Text #2

Max Range: 1.3496. Min Range: -1.3496

Max Act: 1.2242. Min Act: -0.0000

Data Index: 993324 (The Pile)

Max Activating Token Index: 128

Text #3

Max Range: 1.3496. Min Range: -1.3496

Max Act: 1.0664. Min Act: -0.0000

Data Index: 1498809 (The Pile)

Max Activating Token Index: 941

Text #4

Max Range: 1.3496. Min Range: -1.3496

Max Act: 1.0988. Min Act: -0.0000

Data Index: 532349 (The Pile)

Max Activating Token Index: 1010

Text #5

Max Range: 1.3496. Min Range: -1.3496

Max Act: 1.0862. Min Act: -0.0000

Data Index: 1651930 (The Pile)

Max Activating Token Index: 717

Text #6

Max Range: 1.3496. Min Range: -1.3496

Max Act: 1.0523. Min Act: -0.0000

Data Index: 1844543 (The Pile)

Max Activating Token Index: 74

Text #7

Max Range: 1.3496. Min Range: -1.3496

Max Act: 1.0717. Min Act: -0.0000

Data Index: 268387 (The Pile)

Max Activating Token Index: 134

Text #8

Max Range: 1.3496. Min Range: -1.3496

Max Act: 1.0948. Min Act: -0.0000

Data Index: 1462320 (The Pile)

Max Activating Token Index: 206

Text #9

Max Range: 1.3496. Min Range: -1.3496

Max Act: 0.9371. Min Act: -0.0000

Data Index: 957046 (The Pile)

Max Activating Token Index: 868

Text #10

Max Range: 1.3496. Min Range: -1.3496

Max Act: 1.0050. Min Act: -0.0000

Data Index: 619227 (The Pile)

Max Activating Token Index: 77

Text #11

Max Range: 1.3496. Min Range: -1.3496

Max Act: 0.9575. Min Act: -0.0000

Data Index: 871306 (The Pile)

Max Activating Token Index: 151

Text #12

Max Range: 1.3496. Min Range: -1.3496

Max Act: 0.9715. Min Act: -0.0000

Data Index: 1153045 (The Pile)

Max Activating Token Index: 728

Text #13

Max Range: 1.3496. Min Range: -1.3496

Max Act: 0.9080. Min Act: -0.0000

Data Index: 1779100 (The Pile)

Max Activating Token Index: 920

Text #14

Max Range: 1.3496. Min Range: -1.3496

Max Act: 0.9411. Min Act: -0.0000

Data Index: 1213173 (The Pile)

Max Activating Token Index: 495

Text #15

Max Range: 1.3496. Min Range: -1.3496

Max Act: 0.9132. Min Act: -0.0000

Data Index: 591597 (The Pile)

Max Activating Token Index: 981

Text #16

Max Range: 1.3496. Min Range: -1.3496

Max Act: 0.9262. Min Act: -0.0000

Data Index: 94358 (The Pile)

Max Activating Token Index: 610

Text #17

Max Range: 1.3496. Min Range: -1.3496

Max Act: 0.8793. Min Act: -0.0000

Data Index: 1323290 (The Pile)

Max Activating Token Index: 99

Text #18

Max Range: 1.3496. Min Range: -1.3496

Max Act: 0.9488. Min Act: -0.0000

Data Index: 1024100 (The Pile)

Max Activating Token Index: 964

Text #19

Max Range: 1.3496. Min Range: -1.3496

Max Act: 0.9227. Min Act: -0.0000

Data Index: 1066627 (The Pile)

Max Activating Token Index: 319