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

Dataset: The Pile

Neuron 504 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9958. Min Range: -0.9958

Max Act: 0.9958. Min Act: -0.0000

Data Index: 511093 (The Pile)

Max Activating Token Index: 245

Text #1

Max Range: 0.9958. Min Range: -0.9958

Max Act: 0.9191. Min Act: -0.0000

Data Index: 588561 (The Pile)

Max Activating Token Index: 11

Text #2

Max Range: 0.9958. Min Range: -0.9958

Max Act: 0.8660. Min Act: -0.0000

Data Index: 1135906 (The Pile)

Max Activating Token Index: 12

Text #3

Max Range: 0.9958. Min Range: -0.9958

Max Act: 0.8276. Min Act: -0.0000

Data Index: 1448221 (The Pile)

Max Activating Token Index: 10

Text #4

Max Range: 0.9958. Min Range: -0.9958

Max Act: 0.7749. Min Act: -0.0000

Data Index: 439678 (The Pile)

Max Activating Token Index: 21

Text #5

Max Range: 0.9958. Min Range: -0.9958

Max Act: 0.7759. Min Act: -0.0000

Data Index: 1179026 (The Pile)

Max Activating Token Index: 22

Text #6

Max Range: 0.9958. Min Range: -0.9958

Max Act: 0.7816. Min Act: -0.0000

Data Index: 680621 (The Pile)

Max Activating Token Index: 5

Text #7

Max Range: 0.9958. Min Range: -0.9958

Max Act: 0.7570. Min Act: -0.0000

Data Index: 357952 (The Pile)

Max Activating Token Index: 16

Text #8

Max Range: 0.9958. Min Range: -0.9958

Max Act: 0.7734. Min Act: -0.0000

Data Index: 13552 (The Pile)

Max Activating Token Index: 35

Text #9

Max Range: 0.9958. Min Range: -0.9958

Max Act: 0.7764. Min Act: -0.0000

Data Index: 369780 (The Pile)

Max Activating Token Index: 5

Text #10

Max Range: 0.9958. Min Range: -0.9958

Max Act: 0.7694. Min Act: -0.0000

Data Index: 1573570 (The Pile)

Max Activating Token Index: 32

Text #11

Max Range: 0.9958. Min Range: -0.9958

Max Act: 0.7384. Min Act: -0.0000

Data Index: 1080346 (The Pile)

Max Activating Token Index: 9

Text #12

Max Range: 0.9958. Min Range: -0.9958

Max Act: 0.7312. Min Act: -0.0000

Data Index: 376704 (The Pile)

Max Activating Token Index: 8

Text #13

Max Range: 0.9958. Min Range: -0.9958

Max Act: 0.7553. Min Act: -0.0000

Data Index: 1739754 (The Pile)

Max Activating Token Index: 24

Text #14

Max Range: 0.9958. Min Range: -0.9958

Max Act: 0.7104. Min Act: -0.0000

Data Index: 1854218 (The Pile)

Max Activating Token Index: 30

Text #15

Max Range: 0.9958. Min Range: -0.9958

Max Act: 0.7520. Min Act: -0.0000

Data Index: 1452701 (The Pile)

Max Activating Token Index: 6

Text #16

Max Range: 0.9958. Min Range: -0.9958

Max Act: 0.7402. Min Act: -0.0000

Data Index: 62680 (The Pile)

Max Activating Token Index: 10

Text #17

Max Range: 0.9958. Min Range: -0.9958

Max Act: 0.7350. Min Act: -0.0000

Data Index: 1763475 (The Pile)

Max Activating Token Index: 17

Text #18

Max Range: 0.9958. Min Range: -0.9958

Max Act: 0.6875. Min Act: -0.0000

Data Index: 177945 (The Pile)

Max Activating Token Index: 14

Text #19

Max Range: 0.9958. Min Range: -0.9958

Max Act: 0.7460. Min Act: -0.0000

Data Index: 1029471 (The Pile)

Max Activating Token Index: 22