Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1833 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.4677. Min Act: -0.0000

Data Index: 1525327 (The Pile)

Max Activating Token Index: 887

Text #1

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.4524. Min Act: 0.0000

Data Index: 988058 (The Pile)

Max Activating Token Index: 554

Text #2

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.4768. Min Act: -0.0000

Data Index: 1551862 (The Pile)

Max Activating Token Index: 940

Text #3

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.4180. Min Act: -0.0000

Data Index: 1807216 (The Pile)

Max Activating Token Index: 258

Text #4

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.4153. Min Act: -0.0000

Data Index: 284751 (The Pile)

Max Activating Token Index: 664

Text #5

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.4050. Min Act: -0.0000

Data Index: 835056 (The Pile)

Max Activating Token Index: 996

Text #6

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.4009. Min Act: -0.0000

Data Index: 1451244 (The Pile)

Max Activating Token Index: 224

Text #7

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3874. Min Act: -0.0000

Data Index: 285404 (The Pile)

Max Activating Token Index: 117

Text #8

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3820. Min Act: -0.0000

Data Index: 407007 (The Pile)

Max Activating Token Index: 833

Text #9

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3915. Min Act: -0.0000

Data Index: 1048586 (The Pile)

Max Activating Token Index: 83

Text #10

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3923. Min Act: 0.0000

Data Index: 43579 (The Pile)

Max Activating Token Index: 524

Text #11

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3801. Min Act: -0.0000

Data Index: 1113729 (The Pile)

Max Activating Token Index: 1002

Text #12

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3868. Min Act: -0.0000

Data Index: 621385 (The Pile)

Max Activating Token Index: 771

Text #13

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3849. Min Act: -0.0000

Data Index: 1191960 (The Pile)

Max Activating Token Index: 964

Text #14

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3625. Min Act: -0.0000

Data Index: 1798857 (The Pile)

Max Activating Token Index: 14

Text #15

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3686. Min Act: 0.0000

Data Index: 490303 (The Pile)

Max Activating Token Index: 393

Text #16

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3703. Min Act: -0.0000

Data Index: 236727 (The Pile)

Max Activating Token Index: 223

Text #17

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3760. Min Act: 0.0000

Data Index: 711230 (The Pile)

Max Activating Token Index: 182

Text #18

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3645. Min Act: 0.0000

Data Index: 415634 (The Pile)

Max Activating Token Index: 161

Text #19

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3526. Min Act: -0.0000

Data Index: 705434 (The Pile)

Max Activating Token Index: 803