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

Dataset: The Pile

Neuron 4000 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: 0.9975. Min Range: -0.9975

Max Act: 0.9975. Min Act: -0.0000

Data Index: 1160783 (The Pile)

Max Activating Token Index: 11

Text #1

Max Range: 0.9975. Min Range: -0.9975

Max Act: 0.8941. Min Act: -0.0000

Data Index: 997869 (The Pile)

Max Activating Token Index: 32

Text #2

Max Range: 0.9975. Min Range: -0.9975

Max Act: 0.9215. Min Act: -0.0000

Data Index: 1743727 (The Pile)

Max Activating Token Index: 9

Text #3

Max Range: 0.9975. Min Range: -0.9975

Max Act: 0.8886. Min Act: -0.0000

Data Index: 778179 (The Pile)

Max Activating Token Index: 701

Text #4

Max Range: 0.9975. Min Range: -0.9975

Max Act: 0.8807. Min Act: -0.0000

Data Index: 190380 (The Pile)

Max Activating Token Index: 15

Text #5

Max Range: 0.9975. Min Range: -0.9975

Max Act: 0.8419. Min Act: -0.0000

Data Index: 847139 (The Pile)

Max Activating Token Index: 395

Text #6

Max Range: 0.9975. Min Range: -0.9975

Max Act: 0.8043. Min Act: -0.0000

Data Index: 1339835 (The Pile)

Max Activating Token Index: 1013

Text #7

Max Range: 0.9975. Min Range: -0.9975

Max Act: 0.8099. Min Act: -0.0000

Data Index: 1764782 (The Pile)

Max Activating Token Index: 10

Text #8

Max Range: 0.9975. Min Range: -0.9975

Max Act: 0.8191. Min Act: -0.0000

Data Index: 46090 (The Pile)

Max Activating Token Index: 260

Text #9

Max Range: 0.9975. Min Range: -0.9975

Max Act: 0.7966. Min Act: -0.0000

Data Index: 1451381 (The Pile)

Max Activating Token Index: 462

Text #10

Max Range: 0.9975. Min Range: -0.9975

Max Act: 0.7889. Min Act: -0.0000

Data Index: 939479 (The Pile)

Max Activating Token Index: 6

Text #11

Max Range: 0.9975. Min Range: -0.9975

Max Act: 0.7853. Min Act: -0.0000

Data Index: 6265 (The Pile)

Max Activating Token Index: 10

Text #12

Max Range: 0.9975. Min Range: -0.9975

Max Act: 0.8417. Min Act: -0.0000

Data Index: 1226263 (The Pile)

Max Activating Token Index: 852

Text #13

Max Range: 0.9975. Min Range: -0.9975

Max Act: 0.8310. Min Act: -0.0000

Data Index: 435850 (The Pile)

Max Activating Token Index: 274

Text #14

Max Range: 0.9975. Min Range: -0.9975

Max Act: 0.8382. Min Act: -0.0000

Data Index: 941337 (The Pile)

Max Activating Token Index: 6

Text #15

Max Range: 0.9975. Min Range: -0.9975

Max Act: 0.7963. Min Act: -0.0000

Data Index: 395775 (The Pile)

Max Activating Token Index: 87

Text #16

Max Range: 0.9975. Min Range: -0.9975

Max Act: 0.7960. Min Act: -0.0000

Data Index: 255299 (The Pile)

Max Activating Token Index: 12

Text #17

Max Range: 0.9975. Min Range: -0.9975

Max Act: 0.7963. Min Act: -0.0000

Data Index: 1818111 (The Pile)

Max Activating Token Index: 11

Text #18

Max Range: 0.9975. Min Range: -0.9975

Max Act: 0.7733. Min Act: -0.0000

Data Index: 1705580 (The Pile)

Max Activating Token Index: 17

Text #19

Max Range: 0.9975. Min Range: -0.9975

Max Act: 0.7950. Min Act: -0.0000

Data Index: 40191 (The Pile)

Max Activating Token Index: 13