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

Dataset: The Pile

Neuron 3386 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: 0.7967. Min Range: -0.7967

Max Act: 0.7967. Min Act: -0.0000

Data Index: 1526167 (The Pile)

Max Activating Token Index: 147

Text #1

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7312. Min Act: -0.0000

Data Index: 488306 (The Pile)

Max Activating Token Index: 772

Text #2

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7684. Min Act: -0.0000

Data Index: 1456112 (The Pile)

Max Activating Token Index: 1014

Text #3

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7416. Min Act: -0.0000

Data Index: 1473777 (The Pile)

Max Activating Token Index: 352

Text #4

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.6845. Min Act: -0.0000

Data Index: 848914 (The Pile)

Max Activating Token Index: 118

Text #5

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7086. Min Act: -0.0000

Data Index: 1379372 (The Pile)

Max Activating Token Index: 123

Text #6

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7352. Min Act: -0.0000

Data Index: 1134120 (The Pile)

Max Activating Token Index: 255

Text #7

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7616. Min Act: -0.0000

Data Index: 827584 (The Pile)

Max Activating Token Index: 66

Text #8

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.6557. Min Act: -0.0000

Data Index: 950213 (The Pile)

Max Activating Token Index: 64

Text #9

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.6895. Min Act: -0.0000

Data Index: 1280725 (The Pile)

Max Activating Token Index: 87

Text #10

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7217. Min Act: -0.0000

Data Index: 602921 (The Pile)

Max Activating Token Index: 861

Text #11

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7095. Min Act: -0.0000

Data Index: 1791691 (The Pile)

Max Activating Token Index: 216

Text #12

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.6272. Min Act: -0.0000

Data Index: 47602 (The Pile)

Max Activating Token Index: 233

Text #13

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7452. Min Act: -0.0000

Data Index: 1942627 (The Pile)

Max Activating Token Index: 68

Text #14

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.5681. Min Act: -0.0000

Data Index: 1291498 (The Pile)

Max Activating Token Index: 828

Text #15

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.6823. Min Act: -0.0000

Data Index: 1596784 (The Pile)

Max Activating Token Index: 924

Text #16

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.6273. Min Act: -0.0000

Data Index: 1328987 (The Pile)

Max Activating Token Index: 958

Text #17

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7424. Min Act: -0.0000

Data Index: 707498 (The Pile)

Max Activating Token Index: 814

Text #18

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.6646. Min Act: -0.0000

Data Index: 914433 (The Pile)

Max Activating Token Index: 756

Text #19

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.6683. Min Act: -0.0000

Data Index: 1389623 (The Pile)

Max Activating Token Index: 387