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

Dataset: The Pile

Neuron 2990 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: 0.3185. Min Range: -0.3185

Max Act: 0.3185. Min Act: -0.0000

Data Index: 509370 (The Pile)

Max Activating Token Index: 121

Text #1

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2453. Min Act: -0.0000

Data Index: 495797 (The Pile)

Max Activating Token Index: 99

Text #2

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2082. Min Act: -0.0000

Data Index: 410134 (The Pile)

Max Activating Token Index: 409

Text #3

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.1824. Min Act: -0.0000

Data Index: 1562554 (The Pile)

Max Activating Token Index: 734

Text #4

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2000. Min Act: -0.0000

Data Index: 313445 (The Pile)

Max Activating Token Index: 512

Text #5

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.1952. Min Act: -0.0000

Data Index: 463178 (The Pile)

Max Activating Token Index: 793

Text #6

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.1752. Min Act: -0.0000

Data Index: 593848 (The Pile)

Max Activating Token Index: 432

Text #7

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.1412. Min Act: -0.0000

Data Index: 245624 (The Pile)

Max Activating Token Index: 928

Text #8

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.1544. Min Act: -0.0000

Data Index: 613633 (The Pile)

Max Activating Token Index: 811

Text #9

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.1708. Min Act: -0.0000

Data Index: 1995431 (The Pile)

Max Activating Token Index: 338

Text #10

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.1652. Min Act: -0.0000

Data Index: 214997 (The Pile)

Max Activating Token Index: 1012

Text #11

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.1631. Min Act: 0.0000

Data Index: 1327855 (The Pile)

Max Activating Token Index: 263

Text #12

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.1648. Min Act: -0.0000

Data Index: 222588 (The Pile)

Max Activating Token Index: 129

Text #13

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.1501. Min Act: -0.0000

Data Index: 254261 (The Pile)

Max Activating Token Index: 906

Text #14

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.1581. Min Act: -0.0000

Data Index: 1634101 (The Pile)

Max Activating Token Index: 484

Text #15

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.1590. Min Act: -0.0000

Data Index: 1182206 (The Pile)

Max Activating Token Index: 261

Text #16

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.1535. Min Act: -0.0000

Data Index: 1596190 (The Pile)

Max Activating Token Index: 555

Text #17

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.1653. Min Act: -0.0000

Data Index: 830293 (The Pile)

Max Activating Token Index: 633

Text #18

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.1642. Min Act: -0.0000

Data Index: 1745611 (The Pile)

Max Activating Token Index: 124

Text #19

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.1631. Min Act: -0.0000

Data Index: 941371 (The Pile)

Max Activating Token Index: 461