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

Dataset: The Pile

Neuron 3098 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: 0.6572. Min Range: -0.6572

Max Act: 0.6572. Min Act: -0.0000

Data Index: 1493848 (The Pile)

Max Activating Token Index: 104

Text #1

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.6128. Min Act: -0.0000

Data Index: 700965 (The Pile)

Max Activating Token Index: 54

Text #2

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.6277. Min Act: -0.0000

Data Index: 420385 (The Pile)

Max Activating Token Index: 204

Text #3

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.6185. Min Act: -0.0000

Data Index: 605506 (The Pile)

Max Activating Token Index: 127

Text #4

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5976. Min Act: -0.0000

Data Index: 643325 (The Pile)

Max Activating Token Index: 163

Text #5

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5893. Min Act: -0.0000

Data Index: 241519 (The Pile)

Max Activating Token Index: 67

Text #6

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5871. Min Act: -0.0000

Data Index: 1643088 (The Pile)

Max Activating Token Index: 682

Text #7

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5270. Min Act: -0.0000

Data Index: 921459 (The Pile)

Max Activating Token Index: 58

Text #8

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5450. Min Act: -0.0000

Data Index: 1718960 (The Pile)

Max Activating Token Index: 190

Text #9

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5411. Min Act: -0.0000

Data Index: 255205 (The Pile)

Max Activating Token Index: 496

Text #10

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5771. Min Act: -0.0000

Data Index: 1514361 (The Pile)

Max Activating Token Index: 40

Text #11

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5372. Min Act: -0.0000

Data Index: 767715 (The Pile)

Max Activating Token Index: 69

Text #12

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5480. Min Act: -0.0000

Data Index: 1938793 (The Pile)

Max Activating Token Index: 280

Text #13

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5439. Min Act: -0.0000

Data Index: 268226 (The Pile)

Max Activating Token Index: 83

Text #14

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5292. Min Act: -0.0000

Data Index: 358595 (The Pile)

Max Activating Token Index: 468

Text #15

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5442. Min Act: -0.0000

Data Index: 750050 (The Pile)

Max Activating Token Index: 158

Text #16

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5454. Min Act: -0.0000

Data Index: 1463941 (The Pile)

Max Activating Token Index: 232

Text #17

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5196. Min Act: -0.0000

Data Index: 1133774 (The Pile)

Max Activating Token Index: 62

Text #18

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5372. Min Act: -0.0000

Data Index: 1560428 (The Pile)

Max Activating Token Index: 64

Text #19

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5169. Min Act: -0.0000

Data Index: 97070 (The Pile)

Max Activating Token Index: 148