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

Dataset: The Pile

Neuron 1703 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.5085. Min Act: -0.0000

Data Index: 1770585 (The Pile)

Max Activating Token Index: 229

Text #1

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4640. Min Act: -0.0000

Data Index: 848980 (The Pile)

Max Activating Token Index: 556

Text #2

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4383. Min Act: -0.0000

Data Index: 534286 (The Pile)

Max Activating Token Index: 717

Text #3

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4091. Min Act: -0.0000

Data Index: 1501329 (The Pile)

Max Activating Token Index: 323

Text #4

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4259. Min Act: -0.0000

Data Index: 1033606 (The Pile)

Max Activating Token Index: 41

Text #5

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.3993. Min Act: -0.0000

Data Index: 828674 (The Pile)

Max Activating Token Index: 173

Text #6

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.3916. Min Act: -0.0000

Data Index: 941075 (The Pile)

Max Activating Token Index: 238

Text #7

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.3827. Min Act: -0.0000

Data Index: 1003535 (The Pile)

Max Activating Token Index: 161

Text #8

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.3626. Min Act: -0.0000

Data Index: 1980869 (The Pile)

Max Activating Token Index: 63

Text #9

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.3681. Min Act: -0.0000

Data Index: 50929 (The Pile)

Max Activating Token Index: 583

Text #10

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.3611. Min Act: -0.0000

Data Index: 1279483 (The Pile)

Max Activating Token Index: 416

Text #11

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.3696. Min Act: -0.0000

Data Index: 633746 (The Pile)

Max Activating Token Index: 842

Text #12

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.3557. Min Act: -0.0000

Data Index: 1532675 (The Pile)

Max Activating Token Index: 418

Text #13

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.3387. Min Act: -0.0000

Data Index: 1723343 (The Pile)

Max Activating Token Index: 271

Text #14

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.3266. Min Act: -0.0000

Data Index: 1297182 (The Pile)

Max Activating Token Index: 589

Text #15

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.3212. Min Act: -0.0000

Data Index: 1135959 (The Pile)

Max Activating Token Index: 130

Text #16

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.3649. Min Act: -0.0000

Data Index: 1556610 (The Pile)

Max Activating Token Index: 31

Text #17

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.3416. Min Act: -0.0000

Data Index: 1337792 (The Pile)

Max Activating Token Index: 362

Text #18

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.3296. Min Act: -0.0000

Data Index: 1093252 (The Pile)

Max Activating Token Index: 484

Text #19

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.3297. Min Act: -0.0000

Data Index: 180426 (The Pile)

Max Activating Token Index: 23