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

Dataset: The Pile

Neuron 2571 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0709. Min Range: -1.0709

Max Act: 1.0709. Min Act: -0.0000

Data Index: 828488 (The Pile)

Max Activating Token Index: 994

Text #1

Max Range: 1.0709. Min Range: -1.0709

Max Act: 1.0336. Min Act: -0.0000

Data Index: 1212008 (The Pile)

Max Activating Token Index: 403

Text #2

Max Range: 1.0709. Min Range: -1.0709

Max Act: 1.0235. Min Act: -0.0000

Data Index: 395867 (The Pile)

Max Activating Token Index: 48

Text #3

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.9460. Min Act: -0.0000

Data Index: 51949 (The Pile)

Max Activating Token Index: 146

Text #4

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.9236. Min Act: -0.0000

Data Index: 1520742 (The Pile)

Max Activating Token Index: 1008

Text #5

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.9665. Min Act: -0.0000

Data Index: 1230248 (The Pile)

Max Activating Token Index: 411

Text #6

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.9620. Min Act: -0.0000

Data Index: 311932 (The Pile)

Max Activating Token Index: 25

Text #7

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.9018. Min Act: -0.0000

Data Index: 1386086 (The Pile)

Max Activating Token Index: 222

Text #8

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.9474. Min Act: -0.0000

Data Index: 1076571 (The Pile)

Max Activating Token Index: 14

Text #9

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.8895. Min Act: -0.0000

Data Index: 1518163 (The Pile)

Max Activating Token Index: 125

Text #10

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.9380. Min Act: -0.0000

Data Index: 1010429 (The Pile)

Max Activating Token Index: 39

Text #11

Max Range: 1.0709. Min Range: -1.0709

Max Act: 1.0468. Min Act: -0.0000

Data Index: 929130 (The Pile)

Max Activating Token Index: 532

Text #12

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.9822. Min Act: -0.0000

Data Index: 1376084 (The Pile)

Max Activating Token Index: 387

Text #13

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.9230. Min Act: -0.0000

Data Index: 126537 (The Pile)

Max Activating Token Index: 51

Text #14

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.9062. Min Act: -0.0000

Data Index: 1573973 (The Pile)

Max Activating Token Index: 853

Text #15

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.8995. Min Act: -0.0000

Data Index: 1442643 (The Pile)

Max Activating Token Index: 180

Text #16

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.8977. Min Act: -0.0000

Data Index: 991830 (The Pile)

Max Activating Token Index: 522

Text #17

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.8945. Min Act: -0.0000

Data Index: 460087 (The Pile)

Max Activating Token Index: 511

Text #18

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.8975. Min Act: -0.0000

Data Index: 1433964 (The Pile)

Max Activating Token Index: 696

Text #19

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.9539. Min Act: -0.0000

Data Index: 439911 (The Pile)

Max Activating Token Index: 880