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

Dataset: The Pile

Neuron 3265 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: 1.4341. Min Range: -1.4341

Max Act: 1.4341. Min Act: -0.0000

Data Index: 1946163 (The Pile)

Max Activating Token Index: 843

Text #1

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.1968. Min Act: -0.0000

Data Index: 1949676 (The Pile)

Max Activating Token Index: 697

Text #2

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.0221. Min Act: -0.0000

Data Index: 1631917 (The Pile)

Max Activating Token Index: 837

Text #3

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.2090. Min Act: -0.0000

Data Index: 1986835 (The Pile)

Max Activating Token Index: 499

Text #4

Max Range: 1.4341. Min Range: -1.4341

Max Act: 0.9487. Min Act: -0.0000

Data Index: 1015269 (The Pile)

Max Activating Token Index: 739

Text #5

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.1997. Min Act: -0.0000

Data Index: 84406 (The Pile)

Max Activating Token Index: 755

Text #6

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.0626. Min Act: -0.0000

Data Index: 1136410 (The Pile)

Max Activating Token Index: 347

Text #7

Max Range: 1.4341. Min Range: -1.4341

Max Act: 0.9780. Min Act: -0.0000

Data Index: 898619 (The Pile)

Max Activating Token Index: 990

Text #8

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.0825. Min Act: -0.0000

Data Index: 231963 (The Pile)

Max Activating Token Index: 622

Text #9

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.0893. Min Act: -0.0000

Data Index: 1236802 (The Pile)

Max Activating Token Index: 627

Text #10

Max Range: 1.4341. Min Range: -1.4341

Max Act: 0.8828. Min Act: -0.0000

Data Index: 1746110 (The Pile)

Max Activating Token Index: 621

Text #11

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.0531. Min Act: -0.0000

Data Index: 1586902 (The Pile)

Max Activating Token Index: 380

Text #12

Max Range: 1.4341. Min Range: -1.4341

Max Act: 0.9778. Min Act: -0.0000

Data Index: 478366 (The Pile)

Max Activating Token Index: 826

Text #13

Max Range: 1.4341. Min Range: -1.4341

Max Act: 0.8831. Min Act: -0.0000

Data Index: 1792536 (The Pile)

Max Activating Token Index: 390

Text #14

Max Range: 1.4341. Min Range: -1.4341

Max Act: 0.9487. Min Act: -0.0000

Data Index: 1227567 (The Pile)

Max Activating Token Index: 686

Text #15

Max Range: 1.4341. Min Range: -1.4341

Max Act: 0.9760. Min Act: -0.0000

Data Index: 1226032 (The Pile)

Max Activating Token Index: 630

Text #16

Max Range: 1.4341. Min Range: -1.4341

Max Act: 0.9414. Min Act: -0.0000

Data Index: 1794003 (The Pile)

Max Activating Token Index: 715

Text #17

Max Range: 1.4341. Min Range: -1.4341

Max Act: 0.9344. Min Act: -0.0000

Data Index: 1468199 (The Pile)

Max Activating Token Index: 291

Text #18

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.0319. Min Act: -0.0000

Data Index: 750929 (The Pile)

Max Activating Token Index: 817

Text #19

Max Range: 1.4341. Min Range: -1.4341

Max Act: 0.8753. Min Act: -0.0000

Data Index: 1119066 (The Pile)

Max Activating Token Index: 502