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

Dataset: The Pile

Neuron 2857 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0821. Min Range: -1.0821

Max Act: 0.8663. Min Act: -0.0000

Data Index: 689438 (The Pile)

Max Activating Token Index: 674

Text #1

Max Range: 1.0821. Min Range: -1.0821

Max Act: 1.0821. Min Act: -0.0000

Data Index: 1930967 (The Pile)

Max Activating Token Index: 815

Text #2

Max Range: 1.0821. Min Range: -1.0821

Max Act: 0.9511. Min Act: -0.0000

Data Index: 912362 (The Pile)

Max Activating Token Index: 56

Text #3

Max Range: 1.0821. Min Range: -1.0821

Max Act: 0.9944. Min Act: -0.0000

Data Index: 227710 (The Pile)

Max Activating Token Index: 814

Text #4

Max Range: 1.0821. Min Range: -1.0821

Max Act: 0.9491. Min Act: -0.0000

Data Index: 1551549 (The Pile)

Max Activating Token Index: 989

Text #5

Max Range: 1.0821. Min Range: -1.0821

Max Act: 0.8711. Min Act: -0.0000

Data Index: 511752 (The Pile)

Max Activating Token Index: 654

Text #6

Max Range: 1.0821. Min Range: -1.0821

Max Act: 0.9042. Min Act: -0.0000

Data Index: 953425 (The Pile)

Max Activating Token Index: 6

Text #7

Max Range: 1.0821. Min Range: -1.0821

Max Act: 0.8083. Min Act: -0.0000

Data Index: 1174201 (The Pile)

Max Activating Token Index: 815

Text #8

Max Range: 1.0821. Min Range: -1.0821

Max Act: 0.8522. Min Act: -0.0000

Data Index: 698814 (The Pile)

Max Activating Token Index: 796

Text #9

Max Range: 1.0821. Min Range: -1.0821

Max Act: 0.8816. Min Act: -0.0000

Data Index: 1916307 (The Pile)

Max Activating Token Index: 38

Text #10

Max Range: 1.0821. Min Range: -1.0821

Max Act: 0.6929. Min Act: -0.0000

Data Index: 1678622 (The Pile)

Max Activating Token Index: 665

Text #11

Max Range: 1.0821. Min Range: -1.0821

Max Act: 0.9261. Min Act: -0.0000

Data Index: 691644 (The Pile)

Max Activating Token Index: 785

Text #12

Max Range: 1.0821. Min Range: -1.0821

Max Act: 0.8233. Min Act: -0.0000

Data Index: 1561401 (The Pile)

Max Activating Token Index: 831

Text #13

Max Range: 1.0821. Min Range: -1.0821

Max Act: 0.8870. Min Act: -0.0000

Data Index: 850906 (The Pile)

Max Activating Token Index: 213

Text #14

Max Range: 1.0821. Min Range: -1.0821

Max Act: 0.8067. Min Act: -0.0000

Data Index: 38274 (The Pile)

Max Activating Token Index: 966

Text #15

Max Range: 1.0821. Min Range: -1.0821

Max Act: 0.8457. Min Act: -0.0000

Data Index: 1330544 (The Pile)

Max Activating Token Index: 53

Text #16

Max Range: 1.0821. Min Range: -1.0821

Max Act: 0.7940. Min Act: -0.0000

Data Index: 1944373 (The Pile)

Max Activating Token Index: 166

Text #17

Max Range: 1.0821. Min Range: -1.0821

Max Act: 0.7892. Min Act: -0.0000

Data Index: 813710 (The Pile)

Max Activating Token Index: 479

Text #18

Max Range: 1.0821. Min Range: -1.0821

Max Act: 0.8963. Min Act: -0.0000

Data Index: 1613876 (The Pile)

Max Activating Token Index: 453

Text #19

Max Range: 1.0821. Min Range: -1.0821

Max Act: 0.8320. Min Act: -0.0000

Data Index: 1718508 (The Pile)

Max Activating Token Index: 562