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

Dataset: The Pile

Neuron 2849 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: 3.6695. Min Range: -3.6695

Max Act: 3.6695. Min Act: -0.0000

Data Index: 647364 (The Pile)

Max Activating Token Index: 166

Text #1

Max Range: 3.6695. Min Range: -3.6695

Max Act: 3.5656. Min Act: -0.0000

Data Index: 305157 (The Pile)

Max Activating Token Index: 259

Text #2

Max Range: 3.6695. Min Range: -3.6695

Max Act: 3.3439. Min Act: -0.0000

Data Index: 1027438 (The Pile)

Max Activating Token Index: 169

Text #3

Max Range: 3.6695. Min Range: -3.6695

Max Act: 3.3429. Min Act: -0.0000

Data Index: 1783239 (The Pile)

Max Activating Token Index: 894

Text #4

Max Range: 3.6695. Min Range: -3.6695

Max Act: 3.1845. Min Act: -0.0000

Data Index: 464636 (The Pile)

Max Activating Token Index: 32

Text #5

Max Range: 3.6695. Min Range: -3.6695

Max Act: 2.9757. Min Act: -0.0000

Data Index: 1041931 (The Pile)

Max Activating Token Index: 647

Text #6

Max Range: 3.6695. Min Range: -3.6695

Max Act: 2.6184. Min Act: -0.0000

Data Index: 729256 (The Pile)

Max Activating Token Index: 193

Text #7

Max Range: 3.6695. Min Range: -3.6695

Max Act: 2.7874. Min Act: -0.0000

Data Index: 1753108 (The Pile)

Max Activating Token Index: 93

Text #8

Max Range: 3.6695. Min Range: -3.6695

Max Act: 2.7057. Min Act: -0.0000

Data Index: 258996 (The Pile)

Max Activating Token Index: 105

Text #9

Max Range: 3.6695. Min Range: -3.6695

Max Act: 2.7143. Min Act: -0.0000

Data Index: 1717840 (The Pile)

Max Activating Token Index: 60

Text #10

Max Range: 3.6695. Min Range: -3.6695

Max Act: 2.8260. Min Act: -0.0000

Data Index: 867231 (The Pile)

Max Activating Token Index: 499

Text #11

Max Range: 3.6695. Min Range: -3.6695

Max Act: 2.7140. Min Act: -0.0000

Data Index: 811735 (The Pile)

Max Activating Token Index: 57

Text #12

Max Range: 3.6695. Min Range: -3.6695

Max Act: 2.8171. Min Act: -0.0000

Data Index: 1120314 (The Pile)

Max Activating Token Index: 648

Text #13

Max Range: 3.6695. Min Range: -3.6695

Max Act: 2.5151. Min Act: -0.0000

Data Index: 1177252 (The Pile)

Max Activating Token Index: 137

Text #14

Max Range: 3.6695. Min Range: -3.6695

Max Act: 2.6340. Min Act: -0.0000

Data Index: 1939603 (The Pile)

Max Activating Token Index: 557

Text #15

Max Range: 3.6695. Min Range: -3.6695

Max Act: 2.3596. Min Act: -0.0000

Data Index: 1952762 (The Pile)

Max Activating Token Index: 877

Text #16

Max Range: 3.6695. Min Range: -3.6695

Max Act: 2.2243. Min Act: -0.0000

Data Index: 348157 (The Pile)

Max Activating Token Index: 254

Text #17

Max Range: 3.6695. Min Range: -3.6695

Max Act: 2.5334. Min Act: -0.0000

Data Index: 1166906 (The Pile)

Max Activating Token Index: 248

Text #18

Max Range: 3.6695. Min Range: -3.6695

Max Act: 2.3566. Min Act: -0.0000

Data Index: 67044 (The Pile)

Max Activating Token Index: 237

Text #19

Max Range: 3.6695. Min Range: -3.6695

Max Act: 2.1984. Min Act: -0.0000

Data Index: 212305 (The Pile)

Max Activating Token Index: 64