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

Dataset: The Pile

Neuron 2793 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.9955. Min Act: -0.0000

Data Index: 1266355 (The Pile)

Max Activating Token Index: 451

Text #1

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.8776. Min Act: -0.0000

Data Index: 712439 (The Pile)

Max Activating Token Index: 463

Text #2

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.7837. Min Act: -0.0000

Data Index: 1559036 (The Pile)

Max Activating Token Index: 1010

Text #3

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.9489. Min Act: -0.0000

Data Index: 1910516 (The Pile)

Max Activating Token Index: 481

Text #4

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.9413. Min Act: -0.0000

Data Index: 412973 (The Pile)

Max Activating Token Index: 74

Text #5

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.8452. Min Act: -0.0000

Data Index: 1634462 (The Pile)

Max Activating Token Index: 121

Text #6

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.8208. Min Act: -0.0000

Data Index: 1263694 (The Pile)

Max Activating Token Index: 179

Text #7

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.8597. Min Act: -0.0000

Data Index: 1767723 (The Pile)

Max Activating Token Index: 847

Text #8

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.7574. Min Act: -0.0000

Data Index: 594008 (The Pile)

Max Activating Token Index: 160

Text #9

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.7975. Min Act: -0.0000

Data Index: 1033638 (The Pile)

Max Activating Token Index: 43

Text #10

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.7969. Min Act: -0.0000

Data Index: 1336257 (The Pile)

Max Activating Token Index: 21

Text #11

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.9027. Min Act: -0.0000

Data Index: 1976081 (The Pile)

Max Activating Token Index: 757

Text #12

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.7300. Min Act: -0.0000

Data Index: 1026113 (The Pile)

Max Activating Token Index: 661

Text #13

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.7145. Min Act: -0.0000

Data Index: 1492445 (The Pile)

Max Activating Token Index: 977

Text #14

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.8064. Min Act: -0.0000

Data Index: 980919 (The Pile)

Max Activating Token Index: 113

Text #15

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.8591. Min Act: -0.0000

Data Index: 635795 (The Pile)

Max Activating Token Index: 69

Text #16

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.7605. Min Act: -0.0000

Data Index: 1993330 (The Pile)

Max Activating Token Index: 246

Text #17

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.8038. Min Act: -0.0000

Data Index: 1387981 (The Pile)

Max Activating Token Index: 499

Text #18

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.7738. Min Act: -0.0000

Data Index: 1969359 (The Pile)

Max Activating Token Index: 327

Text #19

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.7901. Min Act: -0.0000

Data Index: 1915741 (The Pile)

Max Activating Token Index: 621