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

Dataset: The Pile

Neuron 971 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.4399. Min Act: -0.0000

Data Index: 35810 (The Pile)

Max Activating Token Index: 49

Text #1

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.4777. Min Act: -0.0000

Data Index: 144908 (The Pile)

Max Activating Token Index: 48

Text #2

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.5510. Min Act: -0.0000

Data Index: 34072 (The Pile)

Max Activating Token Index: 49

Text #3

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.2102. Min Act: -0.0000

Data Index: 129718 (The Pile)

Max Activating Token Index: 52

Text #4

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.1833. Min Act: -0.0000

Data Index: 602945 (The Pile)

Max Activating Token Index: 40

Text #5

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.3033. Min Act: -0.0000

Data Index: 1079653 (The Pile)

Max Activating Token Index: 53

Text #6

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.2867. Min Act: -0.0000

Data Index: 1894565 (The Pile)

Max Activating Token Index: 37

Text #7

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.3049. Min Act: -0.0000

Data Index: 137336 (The Pile)

Max Activating Token Index: 48

Text #8

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.2005. Min Act: -0.0000

Data Index: 968062 (The Pile)

Max Activating Token Index: 57

Text #9

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.2778. Min Act: -0.0000

Data Index: 1276905 (The Pile)

Max Activating Token Index: 50

Text #10

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.4108. Min Act: -0.0000

Data Index: 546387 (The Pile)

Max Activating Token Index: 43

Text #11

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.2480. Min Act: -0.0000

Data Index: 1279855 (The Pile)

Max Activating Token Index: 42

Text #12

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.0914. Min Act: -0.0000

Data Index: 513951 (The Pile)

Max Activating Token Index: 74

Text #13

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.2538. Min Act: -0.0000

Data Index: 1945344 (The Pile)

Max Activating Token Index: 46

Text #14

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.3067. Min Act: -0.0000

Data Index: 390305 (The Pile)

Max Activating Token Index: 67

Text #15

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.2189. Min Act: -0.0000

Data Index: 94591 (The Pile)

Max Activating Token Index: 54

Text #16

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.2706. Min Act: -0.0000

Data Index: 1744134 (The Pile)

Max Activating Token Index: 48

Text #17

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.2421. Min Act: -0.0000

Data Index: 63776 (The Pile)

Max Activating Token Index: 36

Text #18

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.0079. Min Act: -0.0000

Data Index: 1732405 (The Pile)

Max Activating Token Index: 105

Text #19

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.1168. Min Act: -0.0000

Data Index: 1467176 (The Pile)

Max Activating Token Index: 71