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

Dataset: The Pile

Neuron 4448 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: 0.5117. Min Range: -0.5117

Max Act: 0.4641. Min Act: -0.0000

Data Index: 1270948 (The Pile)

Max Activating Token Index: 733

Text #1

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.5117. Min Act: -0.0000

Data Index: 1342899 (The Pile)

Max Activating Token Index: 508

Text #2

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.4261. Min Act: -0.0000

Data Index: 134008 (The Pile)

Max Activating Token Index: 711

Text #3

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.4922. Min Act: -0.0000

Data Index: 512737 (The Pile)

Max Activating Token Index: 687

Text #4

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.4607. Min Act: -0.0000

Data Index: 1580243 (The Pile)

Max Activating Token Index: 489

Text #5

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.4391. Min Act: -0.0000

Data Index: 1758519 (The Pile)

Max Activating Token Index: 946

Text #6

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.4370. Min Act: -0.0000

Data Index: 1269997 (The Pile)

Max Activating Token Index: 960

Text #7

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.4563. Min Act: -0.0000

Data Index: 1409193 (The Pile)

Max Activating Token Index: 896

Text #8

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.4409. Min Act: -0.0000

Data Index: 667548 (The Pile)

Max Activating Token Index: 111

Text #9

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.4482. Min Act: -0.0000

Data Index: 147285 (The Pile)

Max Activating Token Index: 258

Text #10

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.4399. Min Act: -0.0000

Data Index: 1078746 (The Pile)

Max Activating Token Index: 567

Text #11

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.4180. Min Act: -0.0000

Data Index: 854998 (The Pile)

Max Activating Token Index: 742

Text #12

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.4049. Min Act: -0.0000

Data Index: 217357 (The Pile)

Max Activating Token Index: 902

Text #13

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.4166. Min Act: -0.0000

Data Index: 1351738 (The Pile)

Max Activating Token Index: 260

Text #14

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.4090. Min Act: -0.0000

Data Index: 549791 (The Pile)

Max Activating Token Index: 217

Text #15

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.4208. Min Act: -0.0000

Data Index: 233699 (The Pile)

Max Activating Token Index: 952

Text #16

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.3814. Min Act: -0.0000

Data Index: 1487997 (The Pile)

Max Activating Token Index: 368

Text #17

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.4159. Min Act: -0.0000

Data Index: 834807 (The Pile)

Max Activating Token Index: 939

Text #18

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.4239. Min Act: -0.0000

Data Index: 1034317 (The Pile)

Max Activating Token Index: 942

Text #19

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.4304. Min Act: -0.0000

Data Index: 1429220 (The Pile)

Max Activating Token Index: 559