Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3774 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5038. Min Range: -2.5038

Max Act: 2.5038. Min Act: -0.0001

Data Index: 400782 (C4 (Web Text))

Max Activating Token Index: 197

Text #1

Max Range: 2.5038. Min Range: -2.5038

Max Act: 2.3188. Min Act: -0.0000

Data Index: 112364 (C4 (Web Text))

Max Activating Token Index: 307

Text #2

Max Range: 2.5038. Min Range: -2.5038

Max Act: 2.1910. Min Act: -0.0000

Data Index: 1173047 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 2.5038. Min Range: -2.5038

Max Act: 2.2512. Min Act: -0.0000

Data Index: 876946 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 2.5038. Min Range: -2.5038

Max Act: 2.0404. Min Act: -0.0000

Data Index: 357200 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 2.5038. Min Range: -2.5038

Max Act: 2.0184. Min Act: -0.0001

Data Index: 337533 (C4 (Web Text))

Max Activating Token Index: 514

Text #6

Max Range: 2.5038. Min Range: -2.5038

Max Act: 2.0056. Min Act: -0.0000

Data Index: 422388 (C4 (Web Text))

Max Activating Token Index: 890

Text #7

Max Range: 2.5038. Min Range: -2.5038

Max Act: 1.9254. Min Act: -0.0000

Data Index: 395553 (C4 (Web Text))

Max Activating Token Index: 569

Text #8

Max Range: 2.5038. Min Range: -2.5038

Max Act: 1.9041. Min Act: -0.0000

Data Index: 1040954 (C4 (Web Text))

Max Activating Token Index: 468

Text #9

Max Range: 2.5038. Min Range: -2.5038

Max Act: 2.2466. Min Act: -0.0000

Data Index: 111212 (C4 (Web Text))

Max Activating Token Index: 296

Text #10

Max Range: 2.5038. Min Range: -2.5038

Max Act: 1.9273. Min Act: -0.0000

Data Index: 490343 (C4 (Web Text))

Max Activating Token Index: 504

Text #11

Max Range: 2.5038. Min Range: -2.5038

Max Act: 1.9237. Min Act: -0.0001

Data Index: 986879 (C4 (Web Text))

Max Activating Token Index: 454

Text #12

Max Range: 2.5038. Min Range: -2.5038

Max Act: 2.0081. Min Act: -0.0000

Data Index: 1328924 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 2.5038. Min Range: -2.5038

Max Act: 2.1307. Min Act: -0.0001

Data Index: 1358577 (C4 (Web Text))

Max Activating Token Index: 344

Text #14

Max Range: 2.5038. Min Range: -2.5038

Max Act: 1.9697. Min Act: -0.0000

Data Index: 859480 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 2.5038. Min Range: -2.5038

Max Act: 1.7752. Min Act: -0.0000

Data Index: 131099 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 2.5038. Min Range: -2.5038

Max Act: 1.9224. Min Act: -0.0001

Data Index: 1258174 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 2.5038. Min Range: -2.5038

Max Act: 1.7213. Min Act: -0.0001

Data Index: 947283 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 2.5038. Min Range: -2.5038

Max Act: 1.8257. Min Act: -0.0000

Data Index: 28133 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 2.5038. Min Range: -2.5038

Max Act: 1.7826. Min Act: -0.0000

Data Index: 353674 (C4 (Web Text))

Max Activating Token Index: 282