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

Dataset: The Pile

Neuron 2991 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: 4.8496. Min Range: -4.8496

Max Act: 4.8496. Min Act: -0.0000

Data Index: 668133 (The Pile)

Max Activating Token Index: 561

Text #1

Max Range: 4.8496. Min Range: -4.8496

Max Act: 4.4039. Min Act: -0.0000

Data Index: 1735421 (The Pile)

Max Activating Token Index: 533

Text #2

Max Range: 4.8496. Min Range: -4.8496

Max Act: 4.2283. Min Act: -0.0000

Data Index: 122037 (The Pile)

Max Activating Token Index: 321

Text #3

Max Range: 4.8496. Min Range: -4.8496

Max Act: 3.7471. Min Act: -0.0000

Data Index: 1159258 (The Pile)

Max Activating Token Index: 944

Text #4

Max Range: 4.8496. Min Range: -4.8496

Max Act: 3.9835. Min Act: -0.0000

Data Index: 229514 (The Pile)

Max Activating Token Index: 465

Text #5

Max Range: 4.8496. Min Range: -4.8496

Max Act: 3.2206. Min Act: -0.0000

Data Index: 362756 (The Pile)

Max Activating Token Index: 919

Text #6

Max Range: 4.8496. Min Range: -4.8496

Max Act: 3.6377. Min Act: -0.0000

Data Index: 701748 (The Pile)

Max Activating Token Index: 673

Text #7

Max Range: 4.8496. Min Range: -4.8496

Max Act: 3.7920. Min Act: -0.0000

Data Index: 671401 (The Pile)

Max Activating Token Index: 252

Text #8

Max Range: 4.8496. Min Range: -4.8496

Max Act: 3.3547. Min Act: -0.0000

Data Index: 150794 (The Pile)

Max Activating Token Index: 535

Text #9

Max Range: 4.8496. Min Range: -4.8496

Max Act: 3.4273. Min Act: -0.0000

Data Index: 1943227 (The Pile)

Max Activating Token Index: 422

Text #10

Max Range: 4.8496. Min Range: -4.8496

Max Act: 3.3266. Min Act: -0.0000

Data Index: 1624860 (The Pile)

Max Activating Token Index: 632

Text #11

Max Range: 4.8496. Min Range: -4.8496

Max Act: 3.0499. Min Act: -0.0000

Data Index: 1168012 (The Pile)

Max Activating Token Index: 770

Text #12

Max Range: 4.8496. Min Range: -4.8496

Max Act: 3.0276. Min Act: -0.0000

Data Index: 766805 (The Pile)

Max Activating Token Index: 610

Text #13

Max Range: 4.8496. Min Range: -4.8496

Max Act: 3.2881. Min Act: -0.0000

Data Index: 1477843 (The Pile)

Max Activating Token Index: 444

Text #14

Max Range: 4.8496. Min Range: -4.8496

Max Act: 2.7864. Min Act: -0.0000

Data Index: 1816786 (The Pile)

Max Activating Token Index: 847

Text #15

Max Range: 4.8496. Min Range: -4.8496

Max Act: 3.2667. Min Act: -0.0000

Data Index: 1083465 (The Pile)

Max Activating Token Index: 343

Text #16

Max Range: 4.8496. Min Range: -4.8496

Max Act: 3.1402. Min Act: -0.0000

Data Index: 1976848 (The Pile)

Max Activating Token Index: 506

Text #17

Max Range: 4.8496. Min Range: -4.8496

Max Act: 3.0924. Min Act: -0.0000

Data Index: 491365 (The Pile)

Max Activating Token Index: 387

Text #18

Max Range: 4.8496. Min Range: -4.8496

Max Act: 3.1262. Min Act: -0.0000

Data Index: 799170 (The Pile)

Max Activating Token Index: 541

Text #19

Max Range: 4.8496. Min Range: -4.8496

Max Act: 3.2882. Min Act: -0.0000

Data Index: 1304398 (The Pile)

Max Activating Token Index: 358