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

Dataset: The Pile

Neuron 3270 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.4422. Min Act: -0.0000

Data Index: 730300 (The Pile)

Max Activating Token Index: 205

Text #1

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.3262. Min Act: -0.0000

Data Index: 1996140 (The Pile)

Max Activating Token Index: 4

Text #2

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.1812. Min Act: -0.0000

Data Index: 1385875 (The Pile)

Max Activating Token Index: 17

Text #3

Max Range: 1.4422. Min Range: -1.4422

Max Act: 0.9734. Min Act: -0.0000

Data Index: 216432 (The Pile)

Max Activating Token Index: 252

Text #4

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.0038. Min Act: -0.0000

Data Index: 512035 (The Pile)

Max Activating Token Index: 14

Text #5

Max Range: 1.4422. Min Range: -1.4422

Max Act: 0.9562. Min Act: -0.0000

Data Index: 1288289 (The Pile)

Max Activating Token Index: 101

Text #6

Max Range: 1.4422. Min Range: -1.4422

Max Act: 0.9966. Min Act: -0.0000

Data Index: 1799049 (The Pile)

Max Activating Token Index: 466

Text #7

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.0352. Min Act: -0.0000

Data Index: 1402567 (The Pile)

Max Activating Token Index: 46

Text #8

Max Range: 1.4422. Min Range: -1.4422

Max Act: 0.9212. Min Act: -0.0000

Data Index: 602810 (The Pile)

Max Activating Token Index: 10

Text #9

Max Range: 1.4422. Min Range: -1.4422

Max Act: 0.9477. Min Act: -0.0000

Data Index: 648465 (The Pile)

Max Activating Token Index: 8

Text #10

Max Range: 1.4422. Min Range: -1.4422

Max Act: 0.9938. Min Act: -0.0000

Data Index: 1152318 (The Pile)

Max Activating Token Index: 14

Text #11

Max Range: 1.4422. Min Range: -1.4422

Max Act: 0.8528. Min Act: -0.0000

Data Index: 1119779 (The Pile)

Max Activating Token Index: 184

Text #12

Max Range: 1.4422. Min Range: -1.4422

Max Act: 0.9549. Min Act: -0.0000

Data Index: 471713 (The Pile)

Max Activating Token Index: 14

Text #13

Max Range: 1.4422. Min Range: -1.4422

Max Act: 0.8956. Min Act: -0.0000

Data Index: 600252 (The Pile)

Max Activating Token Index: 31

Text #14

Max Range: 1.4422. Min Range: -1.4422

Max Act: 0.9121. Min Act: -0.0000

Data Index: 224262 (The Pile)

Max Activating Token Index: 9

Text #15

Max Range: 1.4422. Min Range: -1.4422

Max Act: 0.8800. Min Act: -0.0000

Data Index: 1975897 (The Pile)

Max Activating Token Index: 21

Text #16

Max Range: 1.4422. Min Range: -1.4422

Max Act: 0.9005. Min Act: -0.0000

Data Index: 37298 (The Pile)

Max Activating Token Index: 8

Text #17

Max Range: 1.4422. Min Range: -1.4422

Max Act: 0.8975. Min Act: -0.0000

Data Index: 1203201 (The Pile)

Max Activating Token Index: 21

Text #18

Max Range: 1.4422. Min Range: -1.4422

Max Act: 0.8383. Min Act: -0.0000

Data Index: 868552 (The Pile)

Max Activating Token Index: 7

Text #19

Max Range: 1.4422. Min Range: -1.4422

Max Act: 0.8944. Min Act: -0.0000

Data Index: 864809 (The Pile)

Max Activating Token Index: 12