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

Dataset: The Pile

Neuron 4579 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: 3.3194. Min Range: -3.3194

Max Act: 3.3194. Min Act: -0.0000

Data Index: 172955 (The Pile)

Max Activating Token Index: 83

Text #1

Max Range: 3.3194. Min Range: -3.3194

Max Act: 2.8435. Min Act: -0.0000

Data Index: 318310 (The Pile)

Max Activating Token Index: 47

Text #2

Max Range: 3.3194. Min Range: -3.3194

Max Act: 2.6675. Min Act: -0.0000

Data Index: 1174033 (The Pile)

Max Activating Token Index: 142

Text #3

Max Range: 3.3194. Min Range: -3.3194

Max Act: 2.1553. Min Act: -0.0000

Data Index: 1207907 (The Pile)

Max Activating Token Index: 187

Text #4

Max Range: 3.3194. Min Range: -3.3194

Max Act: 2.1619. Min Act: -0.0000

Data Index: 1480054 (The Pile)

Max Activating Token Index: 801

Text #5

Max Range: 3.3194. Min Range: -3.3194

Max Act: 2.1373. Min Act: -0.0000

Data Index: 862069 (The Pile)

Max Activating Token Index: 107

Text #6

Max Range: 3.3194. Min Range: -3.3194

Max Act: 2.1264. Min Act: -0.0000

Data Index: 1941667 (The Pile)

Max Activating Token Index: 516

Text #7

Max Range: 3.3194. Min Range: -3.3194

Max Act: 2.0113. Min Act: -0.0000

Data Index: 1496658 (The Pile)

Max Activating Token Index: 512

Text #8

Max Range: 3.3194. Min Range: -3.3194

Max Act: 2.0905. Min Act: -0.0000

Data Index: 1665173 (The Pile)

Max Activating Token Index: 125

Text #9

Max Range: 3.3194. Min Range: -3.3194

Max Act: 2.0901. Min Act: -0.0000

Data Index: 883104 (The Pile)

Max Activating Token Index: 16

Text #10

Max Range: 3.3194. Min Range: -3.3194

Max Act: 2.0644. Min Act: -0.0000

Data Index: 1040412 (The Pile)

Max Activating Token Index: 31

Text #11

Max Range: 3.3194. Min Range: -3.3194

Max Act: 2.2911. Min Act: -0.0000

Data Index: 1870077 (The Pile)

Max Activating Token Index: 841

Text #12

Max Range: 3.3194. Min Range: -3.3194

Max Act: 2.0329. Min Act: -0.0000

Data Index: 753290 (The Pile)

Max Activating Token Index: 820

Text #13

Max Range: 3.3194. Min Range: -3.3194

Max Act: 2.0252. Min Act: -0.0000

Data Index: 839947 (The Pile)

Max Activating Token Index: 575

Text #14

Max Range: 3.3194. Min Range: -3.3194

Max Act: 1.8968. Min Act: -0.0000

Data Index: 1495304 (The Pile)

Max Activating Token Index: 496

Text #15

Max Range: 3.3194. Min Range: -3.3194

Max Act: 2.1046. Min Act: -0.0000

Data Index: 266143 (The Pile)

Max Activating Token Index: 105

Text #16

Max Range: 3.3194. Min Range: -3.3194

Max Act: 2.0014. Min Act: -0.0000

Data Index: 890238 (The Pile)

Max Activating Token Index: 346

Text #17

Max Range: 3.3194. Min Range: -3.3194

Max Act: 1.9961. Min Act: -0.0000

Data Index: 425238 (The Pile)

Max Activating Token Index: 45

Text #18

Max Range: 3.3194. Min Range: -3.3194

Max Act: 1.8858. Min Act: -0.0000

Data Index: 1529647 (The Pile)

Max Activating Token Index: 969

Text #19

Max Range: 3.3194. Min Range: -3.3194

Max Act: 1.9862. Min Act: -0.0000

Data Index: 1453414 (The Pile)

Max Activating Token Index: 447