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

Dataset: The Pile

Neuron 3788 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: 0.8757. Min Range: -0.8757

Max Act: 0.8661. Min Act: -0.0000

Data Index: 490092 (The Pile)

Max Activating Token Index: 75

Text #1

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.8223. Min Act: 0.0001

Data Index: 688180 (The Pile)

Max Activating Token Index: 371

Text #2

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.8757. Min Act: -0.0000

Data Index: 1356876 (The Pile)

Max Activating Token Index: 167

Text #3

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.7362. Min Act: -0.0000

Data Index: 1281820 (The Pile)

Max Activating Token Index: 833

Text #4

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.7695. Min Act: -0.0000

Data Index: 799306 (The Pile)

Max Activating Token Index: 875

Text #5

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.7142. Min Act: -0.0001

Data Index: 1981705 (The Pile)

Max Activating Token Index: 1003

Text #6

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.7385. Min Act: -0.0000

Data Index: 678766 (The Pile)

Max Activating Token Index: 851

Text #7

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.6779. Min Act: -0.0000

Data Index: 252776 (The Pile)

Max Activating Token Index: 395

Text #8

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.6726. Min Act: -0.0000

Data Index: 1495535 (The Pile)

Max Activating Token Index: 103

Text #9

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.6976. Min Act: -0.0000

Data Index: 973242 (The Pile)

Max Activating Token Index: 1015

Text #10

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.6479. Min Act: -0.0000

Data Index: 1916591 (The Pile)

Max Activating Token Index: 738

Text #11

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.7710. Min Act: -0.0000

Data Index: 1514774 (The Pile)

Max Activating Token Index: 734

Text #12

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.6933. Min Act: -0.0000

Data Index: 1295484 (The Pile)

Max Activating Token Index: 778

Text #13

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.6525. Min Act: -0.0000

Data Index: 1730381 (The Pile)

Max Activating Token Index: 337

Text #14

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.6613. Min Act: -0.0000

Data Index: 1408805 (The Pile)

Max Activating Token Index: 232

Text #15

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.6500. Min Act: -0.0000

Data Index: 1083849 (The Pile)

Max Activating Token Index: 732

Text #16

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.6161. Min Act: -0.0000

Data Index: 644605 (The Pile)

Max Activating Token Index: 876

Text #17

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.6469. Min Act: 0.0003

Data Index: 462615 (The Pile)

Max Activating Token Index: 119

Text #18

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.6501. Min Act: -0.0000

Data Index: 1081784 (The Pile)

Max Activating Token Index: 490

Text #19

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.6033. Min Act: -0.0000

Data Index: 381872 (The Pile)

Max Activating Token Index: 865