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

Dataset: The Pile

Neuron 1559 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 10.4682. Min Range: -10.4682

Max Act: 10.4682. Min Act: -0.0000

Data Index: 1030220 (The Pile)

Max Activating Token Index: 428

Text #1

Max Range: 10.4682. Min Range: -10.4682

Max Act: 10.3993. Min Act: -0.0000

Data Index: 332086 (The Pile)

Max Activating Token Index: 617

Text #2

Max Range: 10.4682. Min Range: -10.4682

Max Act: 10.4495. Min Act: -0.0000

Data Index: 1148102 (The Pile)

Max Activating Token Index: 972

Text #3

Max Range: 10.4682. Min Range: -10.4682

Max Act: 9.8868. Min Act: -0.0000

Data Index: 61340 (The Pile)

Max Activating Token Index: 182

Text #4

Max Range: 10.4682. Min Range: -10.4682

Max Act: 9.5662. Min Act: -0.0000

Data Index: 810882 (The Pile)

Max Activating Token Index: 836

Text #5

Max Range: 10.4682. Min Range: -10.4682

Max Act: 9.6883. Min Act: -0.0000

Data Index: 1383644 (The Pile)

Max Activating Token Index: 588

Text #6

Max Range: 10.4682. Min Range: -10.4682

Max Act: 8.8519. Min Act: -0.0000

Data Index: 338735 (The Pile)

Max Activating Token Index: 800

Text #7

Max Range: 10.4682. Min Range: -10.4682

Max Act: 8.9998. Min Act: -0.0000

Data Index: 596312 (The Pile)

Max Activating Token Index: 428

Text #8

Max Range: 10.4682. Min Range: -10.4682

Max Act: 9.2458. Min Act: -0.0000

Data Index: 991247 (The Pile)

Max Activating Token Index: 124

Text #9

Max Range: 10.4682. Min Range: -10.4682

Max Act: 8.8863. Min Act: -0.0000

Data Index: 1043569 (The Pile)

Max Activating Token Index: 191

Text #10

Max Range: 10.4682. Min Range: -10.4682

Max Act: 9.0563. Min Act: -0.0000

Data Index: 1066171 (The Pile)

Max Activating Token Index: 303

Text #11

Max Range: 10.4682. Min Range: -10.4682

Max Act: 8.9826. Min Act: -0.0000

Data Index: 554052 (The Pile)

Max Activating Token Index: 711

Text #12

Max Range: 10.4682. Min Range: -10.4682

Max Act: 8.4423. Min Act: -0.0000

Data Index: 18867 (The Pile)

Max Activating Token Index: 214

Text #13

Max Range: 10.4682. Min Range: -10.4682

Max Act: 8.6511. Min Act: -0.0000

Data Index: 642185 (The Pile)

Max Activating Token Index: 306

Text #14

Max Range: 10.4682. Min Range: -10.4682

Max Act: 9.1938. Min Act: -0.0000

Data Index: 774879 (The Pile)

Max Activating Token Index: 66

Text #15

Max Range: 10.4682. Min Range: -10.4682

Max Act: 8.2052. Min Act: -0.0000

Data Index: 89090 (The Pile)

Max Activating Token Index: 221

Text #16

Max Range: 10.4682. Min Range: -10.4682

Max Act: 8.1634. Min Act: -0.0000

Data Index: 768369 (The Pile)

Max Activating Token Index: 292

Text #17

Max Range: 10.4682. Min Range: -10.4682

Max Act: 7.8608. Min Act: -0.0000

Data Index: 665025 (The Pile)

Max Activating Token Index: 895

Text #18

Max Range: 10.4682. Min Range: -10.4682

Max Act: 8.4252. Min Act: -0.0000

Data Index: 450208 (The Pile)

Max Activating Token Index: 778

Text #19

Max Range: 10.4682. Min Range: -10.4682

Max Act: 8.4320. Min Act: -0.0000

Data Index: 377438 (The Pile)

Max Activating Token Index: 116