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

Dataset: The Pile

Neuron 1667 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: 3.8158. Min Range: -3.8158

Max Act: 3.8158. Min Act: -0.0000

Data Index: 979394 (The Pile)

Max Activating Token Index: 272

Text #1

Max Range: 3.8158. Min Range: -3.8158

Max Act: 3.7444. Min Act: -0.0000

Data Index: 1262917 (The Pile)

Max Activating Token Index: 32

Text #2

Max Range: 3.8158. Min Range: -3.8158

Max Act: 3.2243. Min Act: -0.0000

Data Index: 215824 (The Pile)

Max Activating Token Index: 390

Text #3

Max Range: 3.8158. Min Range: -3.8158

Max Act: 3.4941. Min Act: -0.0000

Data Index: 1985514 (The Pile)

Max Activating Token Index: 143

Text #4

Max Range: 3.8158. Min Range: -3.8158

Max Act: 3.2405. Min Act: -0.0000

Data Index: 1420811 (The Pile)

Max Activating Token Index: 611

Text #5

Max Range: 3.8158. Min Range: -3.8158

Max Act: 3.3591. Min Act: -0.0000

Data Index: 1200465 (The Pile)

Max Activating Token Index: 782

Text #6

Max Range: 3.8158. Min Range: -3.8158

Max Act: 3.1038. Min Act: -0.0000

Data Index: 1493680 (The Pile)

Max Activating Token Index: 285

Text #7

Max Range: 3.8158. Min Range: -3.8158

Max Act: 2.9767. Min Act: -0.0000

Data Index: 136583 (The Pile)

Max Activating Token Index: 626

Text #8

Max Range: 3.8158. Min Range: -3.8158

Max Act: 2.7484. Min Act: -0.0000

Data Index: 1447860 (The Pile)

Max Activating Token Index: 954

Text #9

Max Range: 3.8158. Min Range: -3.8158

Max Act: 2.8188. Min Act: -0.0000

Data Index: 794150 (The Pile)

Max Activating Token Index: 146

Text #10

Max Range: 3.8158. Min Range: -3.8158

Max Act: 2.6702. Min Act: -0.0000

Data Index: 828717 (The Pile)

Max Activating Token Index: 551

Text #11

Max Range: 3.8158. Min Range: -3.8158

Max Act: 2.8009. Min Act: -0.0000

Data Index: 330014 (The Pile)

Max Activating Token Index: 155

Text #12

Max Range: 3.8158. Min Range: -3.8158

Max Act: 2.9378. Min Act: -0.0000

Data Index: 414257 (The Pile)

Max Activating Token Index: 95

Text #13

Max Range: 3.8158. Min Range: -3.8158

Max Act: 3.0643. Min Act: -0.0000

Data Index: 455547 (The Pile)

Max Activating Token Index: 151

Text #14

Max Range: 3.8158. Min Range: -3.8158

Max Act: 2.5655. Min Act: -0.0000

Data Index: 1193792 (The Pile)

Max Activating Token Index: 705

Text #15

Max Range: 3.8158. Min Range: -3.8158

Max Act: 2.7008. Min Act: -0.0000

Data Index: 345131 (The Pile)

Max Activating Token Index: 803

Text #16

Max Range: 3.8158. Min Range: -3.8158

Max Act: 2.6996. Min Act: -0.0000

Data Index: 1686079 (The Pile)

Max Activating Token Index: 761

Text #17

Max Range: 3.8158. Min Range: -3.8158

Max Act: 2.5260. Min Act: -0.0000

Data Index: 322554 (The Pile)

Max Activating Token Index: 278

Text #18

Max Range: 3.8158. Min Range: -3.8158

Max Act: 2.5158. Min Act: -0.0000

Data Index: 1612949 (The Pile)

Max Activating Token Index: 190

Text #19

Max Range: 3.8158. Min Range: -3.8158

Max Act: 2.3963. Min Act: -0.0000

Data Index: 669052 (The Pile)

Max Activating Token Index: 78