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

Dataset: The Pile

Neuron 2311 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.5821. Min Act: -0.0000

Data Index: 1087592 (The Pile)

Max Activating Token Index: 628

Text #1

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.4146. Min Act: -0.0000

Data Index: 1460755 (The Pile)

Max Activating Token Index: 865

Text #2

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.4034. Min Act: -0.0000

Data Index: 874719 (The Pile)

Max Activating Token Index: 907

Text #3

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.3786. Min Act: -0.0000

Data Index: 813840 (The Pile)

Max Activating Token Index: 297

Text #4

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.3175. Min Act: -0.0000

Data Index: 746385 (The Pile)

Max Activating Token Index: 942

Text #5

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.3368. Min Act: -0.0000

Data Index: 141998 (The Pile)

Max Activating Token Index: 464

Text #6

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.3432. Min Act: -0.0000

Data Index: 1523751 (The Pile)

Max Activating Token Index: 912

Text #7

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.3266. Min Act: -0.0000

Data Index: 1066173 (The Pile)

Max Activating Token Index: 193

Text #8

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.3887. Min Act: -0.0000

Data Index: 1839757 (The Pile)

Max Activating Token Index: 691

Text #9

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.3310. Min Act: -0.0000

Data Index: 1577194 (The Pile)

Max Activating Token Index: 309

Text #10

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.2845. Min Act: -0.0000

Data Index: 1020403 (The Pile)

Max Activating Token Index: 561

Text #11

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.2917. Min Act: -0.0000

Data Index: 197136 (The Pile)

Max Activating Token Index: 832

Text #12

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.2430. Min Act: -0.0000

Data Index: 690989 (The Pile)

Max Activating Token Index: 285

Text #13

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.2963. Min Act: -0.0000

Data Index: 1801043 (The Pile)

Max Activating Token Index: 735

Text #14

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.3021. Min Act: -0.0000

Data Index: 1506621 (The Pile)

Max Activating Token Index: 699

Text #15

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.2840. Min Act: -0.0000

Data Index: 765005 (The Pile)

Max Activating Token Index: 205

Text #16

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.2965. Min Act: -0.0000

Data Index: 1117194 (The Pile)

Max Activating Token Index: 833

Text #17

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.2512. Min Act: -0.0000

Data Index: 449070 (The Pile)

Max Activating Token Index: 734

Text #18

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.2854. Min Act: -0.0000

Data Index: 274642 (The Pile)

Max Activating Token Index: 524

Text #19

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.2849. Min Act: -0.0000

Data Index: 993040 (The Pile)

Max Activating Token Index: 700