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

Dataset: The Pile

Neuron 1174 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: 0.6052. Min Range: -0.6052

Max Act: 0.6052. Min Act: -0.0000

Data Index: 14317 (The Pile)

Max Activating Token Index: 57

Text #1

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5779. Min Act: -0.0000

Data Index: 769331 (The Pile)

Max Activating Token Index: 942

Text #2

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5716. Min Act: -0.0000

Data Index: 1930288 (The Pile)

Max Activating Token Index: 463

Text #3

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5609. Min Act: -0.0000

Data Index: 1221702 (The Pile)

Max Activating Token Index: 594

Text #4

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5415. Min Act: -0.0000

Data Index: 996292 (The Pile)

Max Activating Token Index: 203

Text #5

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5404. Min Act: -0.0000

Data Index: 978449 (The Pile)

Max Activating Token Index: 546

Text #6

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.4853. Min Act: -0.0000

Data Index: 883437 (The Pile)

Max Activating Token Index: 114

Text #7

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5287. Min Act: -0.0000

Data Index: 1243653 (The Pile)

Max Activating Token Index: 1011

Text #8

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.4832. Min Act: -0.0000

Data Index: 418412 (The Pile)

Max Activating Token Index: 236

Text #9

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5030. Min Act: -0.0000

Data Index: 1308590 (The Pile)

Max Activating Token Index: 923

Text #10

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5266. Min Act: -0.0000

Data Index: 524547 (The Pile)

Max Activating Token Index: 22

Text #11

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5029. Min Act: -0.0000

Data Index: 1375116 (The Pile)

Max Activating Token Index: 461

Text #12

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5156. Min Act: -0.0000

Data Index: 542268 (The Pile)

Max Activating Token Index: 61

Text #13

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5006. Min Act: -0.0000

Data Index: 705432 (The Pile)

Max Activating Token Index: 518

Text #14

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5081. Min Act: -0.0000

Data Index: 69644 (The Pile)

Max Activating Token Index: 405

Text #15

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.4729. Min Act: -0.0000

Data Index: 705999 (The Pile)

Max Activating Token Index: 132

Text #16

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.4934. Min Act: -0.0000

Data Index: 608935 (The Pile)

Max Activating Token Index: 594

Text #17

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.4688. Min Act: -0.0000

Data Index: 1344861 (The Pile)

Max Activating Token Index: 629

Text #18

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.4506. Min Act: -0.0000

Data Index: 791947 (The Pile)

Max Activating Token Index: 668

Text #19

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.4902. Min Act: -0.0000

Data Index: 1510253 (The Pile)

Max Activating Token Index: 112