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

Dataset: The Pile

Neuron 2145 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: 3.8503. Min Range: -3.8503

Max Act: 3.8503. Min Act: -0.0000

Data Index: 855125 (The Pile)

Max Activating Token Index: 778

Text #1

Max Range: 3.8503. Min Range: -3.8503

Max Act: 3.3600. Min Act: -0.0000

Data Index: 379594 (The Pile)

Max Activating Token Index: 630

Text #2

Max Range: 3.8503. Min Range: -3.8503

Max Act: 2.9817. Min Act: -0.0000

Data Index: 1156340 (The Pile)

Max Activating Token Index: 60

Text #3

Max Range: 3.8503. Min Range: -3.8503

Max Act: 3.2037. Min Act: -0.0000

Data Index: 251815 (The Pile)

Max Activating Token Index: 49

Text #4

Max Range: 3.8503. Min Range: -3.8503

Max Act: 3.5432. Min Act: -0.0000

Data Index: 1686825 (The Pile)

Max Activating Token Index: 206

Text #5

Max Range: 3.8503. Min Range: -3.8503

Max Act: 3.1258. Min Act: -0.0000

Data Index: 1645061 (The Pile)

Max Activating Token Index: 944

Text #6

Max Range: 3.8503. Min Range: -3.8503

Max Act: 2.7362. Min Act: -0.0000

Data Index: 1384810 (The Pile)

Max Activating Token Index: 498

Text #7

Max Range: 3.8503. Min Range: -3.8503

Max Act: 2.9836. Min Act: -0.0000

Data Index: 989582 (The Pile)

Max Activating Token Index: 406

Text #8

Max Range: 3.8503. Min Range: -3.8503

Max Act: 2.7924. Min Act: -0.0000

Data Index: 1355083 (The Pile)

Max Activating Token Index: 79

Text #9

Max Range: 3.8503. Min Range: -3.8503

Max Act: 2.7907. Min Act: -0.0000

Data Index: 1478442 (The Pile)

Max Activating Token Index: 76

Text #10

Max Range: 3.8503. Min Range: -3.8503

Max Act: 2.6198. Min Act: -0.0000

Data Index: 114180 (The Pile)

Max Activating Token Index: 973

Text #11

Max Range: 3.8503. Min Range: -3.8503

Max Act: 2.7132. Min Act: -0.0000

Data Index: 827868 (The Pile)

Max Activating Token Index: 887

Text #12

Max Range: 3.8503. Min Range: -3.8503

Max Act: 2.4359. Min Act: -0.0000

Data Index: 1583568 (The Pile)

Max Activating Token Index: 167

Text #13

Max Range: 3.8503. Min Range: -3.8503

Max Act: 2.6781. Min Act: -0.0000

Data Index: 180119 (The Pile)

Max Activating Token Index: 1013

Text #14

Max Range: 3.8503. Min Range: -3.8503

Max Act: 2.8227. Min Act: -0.0000

Data Index: 1567503 (The Pile)

Max Activating Token Index: 628

Text #15

Max Range: 3.8503. Min Range: -3.8503

Max Act: 2.6501. Min Act: -0.0000

Data Index: 746685 (The Pile)

Max Activating Token Index: 76

Text #16

Max Range: 3.8503. Min Range: -3.8503

Max Act: 2.9442. Min Act: -0.0000

Data Index: 1909881 (The Pile)

Max Activating Token Index: 771

Text #17

Max Range: 3.8503. Min Range: -3.8503

Max Act: 2.7804. Min Act: -0.0000

Data Index: 249046 (The Pile)

Max Activating Token Index: 643

Text #18

Max Range: 3.8503. Min Range: -3.8503

Max Act: 2.3191. Min Act: -0.0000

Data Index: 1511743 (The Pile)

Max Activating Token Index: 949

Text #19

Max Range: 3.8503. Min Range: -3.8503

Max Act: 2.5397. Min Act: -0.0000

Data Index: 646894 (The Pile)

Max Activating Token Index: 613