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

Dataset: The Pile

Neuron 664 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: 1.3478. Min Range: -1.3478

Max Act: 1.3246. Min Act: -0.0000

Data Index: 966565 (The Pile)

Max Activating Token Index: 7

Text #1

Max Range: 1.3478. Min Range: -1.3478

Max Act: 1.3478. Min Act: -0.0000

Data Index: 302647 (The Pile)

Max Activating Token Index: 27

Text #2

Max Range: 1.3478. Min Range: -1.3478

Max Act: 1.1344. Min Act: -0.0000

Data Index: 677497 (The Pile)

Max Activating Token Index: 309

Text #3

Max Range: 1.3478. Min Range: -1.3478

Max Act: 1.0561. Min Act: -0.0000

Data Index: 1609870 (The Pile)

Max Activating Token Index: 6

Text #4

Max Range: 1.3478. Min Range: -1.3478

Max Act: 1.0612. Min Act: -0.0000

Data Index: 1333118 (The Pile)

Max Activating Token Index: 4

Text #5

Max Range: 1.3478. Min Range: -1.3478

Max Act: 1.0331. Min Act: -0.0000

Data Index: 672774 (The Pile)

Max Activating Token Index: 4

Text #6

Max Range: 1.3478. Min Range: -1.3478

Max Act: 1.0973. Min Act: 0.0001

Data Index: 1982538 (The Pile)

Max Activating Token Index: 16

Text #7

Max Range: 1.3478. Min Range: -1.3478

Max Act: 0.9983. Min Act: -0.0000

Data Index: 1705036 (The Pile)

Max Activating Token Index: 4

Text #8

Max Range: 1.3478. Min Range: -1.3478

Max Act: 0.9948. Min Act: -0.0000

Data Index: 709558 (The Pile)

Max Activating Token Index: 5

Text #9

Max Range: 1.3478. Min Range: -1.3478

Max Act: 0.9646. Min Act: -0.0000

Data Index: 675853 (The Pile)

Max Activating Token Index: 5

Text #10

Max Range: 1.3478. Min Range: -1.3478

Max Act: 1.0628. Min Act: -0.0000

Data Index: 54973 (The Pile)

Max Activating Token Index: 9

Text #11

Max Range: 1.3478. Min Range: -1.3478

Max Act: 0.9814. Min Act: -0.0000

Data Index: 709243 (The Pile)

Max Activating Token Index: 21

Text #12

Max Range: 1.3478. Min Range: -1.3478

Max Act: 0.9012. Min Act: -0.0000

Data Index: 884307 (The Pile)

Max Activating Token Index: 4

Text #13

Max Range: 1.3478. Min Range: -1.3478

Max Act: 0.9118. Min Act: -0.0000

Data Index: 677429 (The Pile)

Max Activating Token Index: 6

Text #14

Max Range: 1.3478. Min Range: -1.3478

Max Act: 0.9502. Min Act: -0.0000

Data Index: 967379 (The Pile)

Max Activating Token Index: 7

Text #15

Max Range: 1.3478. Min Range: -1.3478

Max Act: 0.9237. Min Act: -0.0000

Data Index: 100950 (The Pile)

Max Activating Token Index: 5

Text #16

Max Range: 1.3478. Min Range: -1.3478

Max Act: 0.9858. Min Act: -0.0000

Data Index: 1441260 (The Pile)

Max Activating Token Index: 6

Text #17

Max Range: 1.3478. Min Range: -1.3478

Max Act: 0.9579. Min Act: -0.0000

Data Index: 478429 (The Pile)

Max Activating Token Index: 4

Text #18

Max Range: 1.3478. Min Range: -1.3478

Max Act: 0.8978. Min Act: -0.0000

Data Index: 1074900 (The Pile)

Max Activating Token Index: 221

Text #19

Max Range: 1.3478. Min Range: -1.3478

Max Act: 0.8621. Min Act: -0.0000

Data Index: 200372 (The Pile)

Max Activating Token Index: 4