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

Dataset: The Pile

Neuron 782 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: 1.1983. Min Range: -1.1983

Max Act: 1.1983. Min Act: -0.0000

Data Index: 1953533 (The Pile)

Max Activating Token Index: 904

Text #1

Max Range: 1.1983. Min Range: -1.1983

Max Act: 1.1139. Min Act: -0.0000

Data Index: 1600511 (The Pile)

Max Activating Token Index: 73

Text #2

Max Range: 1.1983. Min Range: -1.1983

Max Act: 1.1023. Min Act: -0.0000

Data Index: 761210 (The Pile)

Max Activating Token Index: 236

Text #3

Max Range: 1.1983. Min Range: -1.1983

Max Act: 0.9780. Min Act: -0.0000

Data Index: 1351928 (The Pile)

Max Activating Token Index: 676

Text #4

Max Range: 1.1983. Min Range: -1.1983

Max Act: 0.9028. Min Act: -0.0000

Data Index: 1950331 (The Pile)

Max Activating Token Index: 60

Text #5

Max Range: 1.1983. Min Range: -1.1983

Max Act: 0.8536. Min Act: -0.0000

Data Index: 1622055 (The Pile)

Max Activating Token Index: 995

Text #6

Max Range: 1.1983. Min Range: -1.1983

Max Act: 0.9054. Min Act: -0.0000

Data Index: 1699644 (The Pile)

Max Activating Token Index: 114

Text #7

Max Range: 1.1983. Min Range: -1.1983

Max Act: 0.9178. Min Act: -0.0000

Data Index: 251825 (The Pile)

Max Activating Token Index: 91

Text #8

Max Range: 1.1983. Min Range: -1.1983

Max Act: 0.9004. Min Act: -0.0000

Data Index: 1350879 (The Pile)

Max Activating Token Index: 692

Text #9

Max Range: 1.1983. Min Range: -1.1983

Max Act: 0.8421. Min Act: -0.0000

Data Index: 1598057 (The Pile)

Max Activating Token Index: 584

Text #10

Max Range: 1.1983. Min Range: -1.1983

Max Act: 0.8649. Min Act: -0.0000

Data Index: 1615994 (The Pile)

Max Activating Token Index: 107

Text #11

Max Range: 1.1983. Min Range: -1.1983

Max Act: 0.8847. Min Act: -0.0000

Data Index: 1164175 (The Pile)

Max Activating Token Index: 142

Text #12

Max Range: 1.1983. Min Range: -1.1983

Max Act: 0.8451. Min Act: -0.0000

Data Index: 1093503 (The Pile)

Max Activating Token Index: 379

Text #13

Max Range: 1.1983. Min Range: -1.1983

Max Act: 0.8491. Min Act: -0.0000

Data Index: 512779 (The Pile)

Max Activating Token Index: 385

Text #14

Max Range: 1.1983. Min Range: -1.1983

Max Act: 0.8650. Min Act: -0.0000

Data Index: 101089 (The Pile)

Max Activating Token Index: 80

Text #15

Max Range: 1.1983. Min Range: -1.1983

Max Act: 0.8630. Min Act: -0.0000

Data Index: 1648595 (The Pile)

Max Activating Token Index: 313

Text #16

Max Range: 1.1983. Min Range: -1.1983

Max Act: 0.8496. Min Act: -0.0000

Data Index: 1337319 (The Pile)

Max Activating Token Index: 243

Text #17

Max Range: 1.1983. Min Range: -1.1983

Max Act: 0.8052. Min Act: -0.0000

Data Index: 1025142 (The Pile)

Max Activating Token Index: 99

Text #18

Max Range: 1.1983. Min Range: -1.1983

Max Act: 0.7940. Min Act: -0.0000

Data Index: 493577 (The Pile)

Max Activating Token Index: 387

Text #19

Max Range: 1.1983. Min Range: -1.1983

Max Act: 0.8034. Min Act: -0.0000

Data Index: 908412 (The Pile)

Max Activating Token Index: 629