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

Dataset: The Pile

Neuron 1325 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7049. Min Range: -0.7049

Max Act: 0.7049. Min Act: -0.0000

Data Index: 1774491 (The Pile)

Max Activating Token Index: 684

Text #1

Max Range: 0.7049. Min Range: -0.7049

Max Act: 0.5252. Min Act: -0.0000

Data Index: 1859142 (The Pile)

Max Activating Token Index: 496

Text #2

Max Range: 0.7049. Min Range: -0.7049

Max Act: 0.5102. Min Act: -0.0000

Data Index: 1650911 (The Pile)

Max Activating Token Index: 626

Text #3

Max Range: 0.7049. Min Range: -0.7049

Max Act: 0.4515. Min Act: -0.0000

Data Index: 1691283 (The Pile)

Max Activating Token Index: 144

Text #4

Max Range: 0.7049. Min Range: -0.7049

Max Act: 0.4902. Min Act: -0.0000

Data Index: 239107 (The Pile)

Max Activating Token Index: 427

Text #5

Max Range: 0.7049. Min Range: -0.7049

Max Act: 0.5553. Min Act: -0.0000

Data Index: 1079812 (The Pile)

Max Activating Token Index: 41

Text #6

Max Range: 0.7049. Min Range: -0.7049

Max Act: 0.4568. Min Act: -0.0000

Data Index: 1114748 (The Pile)

Max Activating Token Index: 272

Text #7

Max Range: 0.7049. Min Range: -0.7049

Max Act: 0.4272. Min Act: -0.0000

Data Index: 107858 (The Pile)

Max Activating Token Index: 132

Text #8

Max Range: 0.7049. Min Range: -0.7049

Max Act: 0.3990. Min Act: -0.0000

Data Index: 937057 (The Pile)

Max Activating Token Index: 673

Text #9

Max Range: 0.7049. Min Range: -0.7049

Max Act: 0.4218. Min Act: -0.0000

Data Index: 242789 (The Pile)

Max Activating Token Index: 104

Text #10

Max Range: 0.7049. Min Range: -0.7049

Max Act: 0.4214. Min Act: -0.0000

Data Index: 1262143 (The Pile)

Max Activating Token Index: 502

Text #11

Max Range: 0.7049. Min Range: -0.7049

Max Act: 0.4404. Min Act: -0.0000

Data Index: 287908 (The Pile)

Max Activating Token Index: 489

Text #12

Max Range: 0.7049. Min Range: -0.7049

Max Act: 0.3782. Min Act: -0.0000

Data Index: 1383047 (The Pile)

Max Activating Token Index: 557

Text #13

Max Range: 0.7049. Min Range: -0.7049

Max Act: 0.4268. Min Act: -0.0000

Data Index: 175081 (The Pile)

Max Activating Token Index: 185

Text #14

Max Range: 0.7049. Min Range: -0.7049

Max Act: 0.4446. Min Act: -0.0000

Data Index: 971723 (The Pile)

Max Activating Token Index: 173

Text #15

Max Range: 0.7049. Min Range: -0.7049

Max Act: 0.3967. Min Act: -0.0000

Data Index: 1887087 (The Pile)

Max Activating Token Index: 478

Text #16

Max Range: 0.7049. Min Range: -0.7049

Max Act: 0.3497. Min Act: -0.0000

Data Index: 492098 (The Pile)

Max Activating Token Index: 481

Text #17

Max Range: 0.7049. Min Range: -0.7049

Max Act: 0.3786. Min Act: -0.0000

Data Index: 1574180 (The Pile)

Max Activating Token Index: 842

Text #18

Max Range: 0.7049. Min Range: -0.7049

Max Act: 0.3410. Min Act: -0.0000

Data Index: 221833 (The Pile)

Max Activating Token Index: 978

Text #19

Max Range: 0.7049. Min Range: -0.7049

Max Act: 0.3693. Min Act: -0.0000

Data Index: 1769711 (The Pile)

Max Activating Token Index: 818