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

Dataset: The Pile

Neuron 1883 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1323. Min Range: -1.1323

Max Act: 0.9883. Min Act: -0.0000

Data Index: 50380 (The Pile)

Max Activating Token Index: 193

Text #1

Max Range: 1.1323. Min Range: -1.1323

Max Act: 1.1323. Min Act: -0.0000

Data Index: 1340217 (The Pile)

Max Activating Token Index: 742

Text #2

Max Range: 1.1323. Min Range: -1.1323

Max Act: 0.8681. Min Act: -0.0000

Data Index: 599056 (The Pile)

Max Activating Token Index: 771

Text #3

Max Range: 1.1323. Min Range: -1.1323

Max Act: 0.8984. Min Act: -0.0000

Data Index: 396552 (The Pile)

Max Activating Token Index: 90

Text #4

Max Range: 1.1323. Min Range: -1.1323

Max Act: 0.9128. Min Act: -0.0000

Data Index: 1123553 (The Pile)

Max Activating Token Index: 440

Text #5

Max Range: 1.1323. Min Range: -1.1323

Max Act: 0.7990. Min Act: -0.0000

Data Index: 1544264 (The Pile)

Max Activating Token Index: 184

Text #6

Max Range: 1.1323. Min Range: -1.1323

Max Act: 0.8351. Min Act: -0.0000

Data Index: 1493593 (The Pile)

Max Activating Token Index: 555

Text #7

Max Range: 1.1323. Min Range: -1.1323

Max Act: 0.8812. Min Act: -0.0000

Data Index: 478189 (The Pile)

Max Activating Token Index: 63

Text #8

Max Range: 1.1323. Min Range: -1.1323

Max Act: 0.8093. Min Act: -0.0000

Data Index: 728328 (The Pile)

Max Activating Token Index: 332

Text #9

Max Range: 1.1323. Min Range: -1.1323

Max Act: 0.7321. Min Act: -0.0000

Data Index: 213227 (The Pile)

Max Activating Token Index: 986

Text #10

Max Range: 1.1323. Min Range: -1.1323

Max Act: 0.6878. Min Act: -0.0000

Data Index: 1584472 (The Pile)

Max Activating Token Index: 863

Text #11

Max Range: 1.1323. Min Range: -1.1323

Max Act: 0.8879. Min Act: -0.0000

Data Index: 279997 (The Pile)

Max Activating Token Index: 55

Text #12

Max Range: 1.1323. Min Range: -1.1323

Max Act: 0.7967. Min Act: -0.0000

Data Index: 858866 (The Pile)

Max Activating Token Index: 309

Text #13

Max Range: 1.1323. Min Range: -1.1323

Max Act: 0.7642. Min Act: -0.0000

Data Index: 495558 (The Pile)

Max Activating Token Index: 454

Text #14

Max Range: 1.1323. Min Range: -1.1323

Max Act: 0.7576. Min Act: -0.0000

Data Index: 1219817 (The Pile)

Max Activating Token Index: 763

Text #15

Max Range: 1.1323. Min Range: -1.1323

Max Act: 0.6837. Min Act: -0.0000

Data Index: 1963086 (The Pile)

Max Activating Token Index: 968

Text #16

Max Range: 1.1323. Min Range: -1.1323

Max Act: 0.7429. Min Act: -0.0000

Data Index: 1796339 (The Pile)

Max Activating Token Index: 168

Text #17

Max Range: 1.1323. Min Range: -1.1323

Max Act: 0.6627. Min Act: -0.0000

Data Index: 132449 (The Pile)

Max Activating Token Index: 177

Text #18

Max Range: 1.1323. Min Range: -1.1323

Max Act: 0.7419. Min Act: -0.0000

Data Index: 1768506 (The Pile)

Max Activating Token Index: 272

Text #19

Max Range: 1.1323. Min Range: -1.1323

Max Act: 0.6383. Min Act: -0.0000

Data Index: 252119 (The Pile)

Max Activating Token Index: 170