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

Dataset: The Pile

Neuron 4703 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9965. Min Range: -1.9965

Max Act: 1.9965. Min Act: -0.0000

Data Index: 537210 (The Pile)

Max Activating Token Index: 684

Text #1

Max Range: 1.9965. Min Range: -1.9965

Max Act: 1.7362. Min Act: -0.0000

Data Index: 692478 (The Pile)

Max Activating Token Index: 759

Text #2

Max Range: 1.9965. Min Range: -1.9965

Max Act: 1.5603. Min Act: -0.0000

Data Index: 1944132 (The Pile)

Max Activating Token Index: 66

Text #3

Max Range: 1.9965. Min Range: -1.9965

Max Act: 1.5171. Min Act: -0.0000

Data Index: 1961122 (The Pile)

Max Activating Token Index: 268

Text #4

Max Range: 1.9965. Min Range: -1.9965

Max Act: 1.4252. Min Act: -0.0000

Data Index: 793027 (The Pile)

Max Activating Token Index: 312

Text #5

Max Range: 1.9965. Min Range: -1.9965

Max Act: 1.3556. Min Act: -0.0000

Data Index: 1933586 (The Pile)

Max Activating Token Index: 728

Text #6

Max Range: 1.9965. Min Range: -1.9965

Max Act: 1.2957. Min Act: -0.0000

Data Index: 880702 (The Pile)

Max Activating Token Index: 490

Text #7

Max Range: 1.9965. Min Range: -1.9965

Max Act: 1.2745. Min Act: -0.0000

Data Index: 1442233 (The Pile)

Max Activating Token Index: 122

Text #8

Max Range: 1.9965. Min Range: -1.9965

Max Act: 1.1993. Min Act: -0.0000

Data Index: 1655451 (The Pile)

Max Activating Token Index: 949

Text #9

Max Range: 1.9965. Min Range: -1.9965

Max Act: 1.1884. Min Act: -0.0000

Data Index: 1248401 (The Pile)

Max Activating Token Index: 947

Text #10

Max Range: 1.9965. Min Range: -1.9965

Max Act: 1.2707. Min Act: -0.0000

Data Index: 1973616 (The Pile)

Max Activating Token Index: 150

Text #11

Max Range: 1.9965. Min Range: -1.9965

Max Act: 1.2976. Min Act: -0.0000

Data Index: 1786426 (The Pile)

Max Activating Token Index: 676

Text #12

Max Range: 1.9965. Min Range: -1.9965

Max Act: 1.1606. Min Act: -0.0000

Data Index: 685924 (The Pile)

Max Activating Token Index: 262

Text #13

Max Range: 1.9965. Min Range: -1.9965

Max Act: 1.2033. Min Act: -0.0000

Data Index: 1825239 (The Pile)

Max Activating Token Index: 377

Text #14

Max Range: 1.9965. Min Range: -1.9965

Max Act: 1.2451. Min Act: -0.0000

Data Index: 1130239 (The Pile)

Max Activating Token Index: 932

Text #15

Max Range: 1.9965. Min Range: -1.9965

Max Act: 1.1613. Min Act: -0.0000

Data Index: 208292 (The Pile)

Max Activating Token Index: 1020

Text #16

Max Range: 1.9965. Min Range: -1.9965

Max Act: 1.0860. Min Act: -0.0000

Data Index: 32032 (The Pile)

Max Activating Token Index: 519

Text #17

Max Range: 1.9965. Min Range: -1.9965

Max Act: 1.0705. Min Act: -0.0000

Data Index: 1600552 (The Pile)

Max Activating Token Index: 851

Text #18

Max Range: 1.9965. Min Range: -1.9965

Max Act: 1.0845. Min Act: -0.0000

Data Index: 1184192 (The Pile)

Max Activating Token Index: 272

Text #19

Max Range: 1.9965. Min Range: -1.9965

Max Act: 1.2038. Min Act: -0.0000

Data Index: 1614690 (The Pile)

Max Activating Token Index: 943