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

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

Neuron 1216 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4286. Min Range: -1.4286

Max Act: 1.4286. Min Act: -0.0000

Data Index: 1023113 (C4 (Web Text))

Max Activating Token Index: 531

Text #1

Max Range: 1.4286. Min Range: -1.4286

Max Act: 1.0679. Min Act: -0.0000

Data Index: 137267 (C4 (Web Text))

Max Activating Token Index: 353

Text #2

Max Range: 1.4286. Min Range: -1.4286

Max Act: 1.1057. Min Act: -0.0000

Data Index: 1289254 (C4 (Web Text))

Max Activating Token Index: 401

Text #3

Max Range: 1.4286. Min Range: -1.4286

Max Act: 1.0670. Min Act: -0.0000

Data Index: 1178159 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 1.4286. Min Range: -1.4286

Max Act: 0.9244. Min Act: -0.0000

Data Index: 1058128 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 1.4286. Min Range: -1.4286

Max Act: 0.9364. Min Act: -0.0000

Data Index: 480925 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 1.4286. Min Range: -1.4286

Max Act: 0.9464. Min Act: -0.0000

Data Index: 1591598 (Python Code)

Max Activating Token Index: 983

Text #7

Max Range: 1.4286. Min Range: -1.4286

Max Act: 0.9243. Min Act: -0.0000

Data Index: 169064 (C4 (Web Text))

Max Activating Token Index: 564

Text #8

Max Range: 1.4286. Min Range: -1.4286

Max Act: 0.9837. Min Act: -0.0000

Data Index: 6625 (C4 (Web Text))

Max Activating Token Index: 970

Text #9

Max Range: 1.4286. Min Range: -1.4286

Max Act: 0.9561. Min Act: -0.0000

Data Index: 1313378 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 1.4286. Min Range: -1.4286

Max Act: 0.8965. Min Act: -0.0000

Data Index: 495634 (C4 (Web Text))

Max Activating Token Index: 718

Text #11

Max Range: 1.4286. Min Range: -1.4286

Max Act: 0.8932. Min Act: -0.0000

Data Index: 1404133 (Python Code)

Max Activating Token Index: 244

Text #12

Max Range: 1.4286. Min Range: -1.4286

Max Act: 0.8421. Min Act: -0.0000

Data Index: 1579520 (Python Code)

Max Activating Token Index: 978

Text #13

Max Range: 1.4286. Min Range: -1.4286

Max Act: 0.8639. Min Act: -0.0000

Data Index: 1465741 (Python Code)

Max Activating Token Index: 996

Text #14

Max Range: 1.4286. Min Range: -1.4286

Max Act: 0.8527. Min Act: -0.0000

Data Index: 14017 (C4 (Web Text))

Max Activating Token Index: 139

Text #15

Max Range: 1.4286. Min Range: -1.4286

Max Act: 0.8474. Min Act: -0.0000

Data Index: 162577 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 1.4286. Min Range: -1.4286

Max Act: 0.8419. Min Act: -0.0000

Data Index: 1626717 (Python Code)

Max Activating Token Index: 803

Text #17

Max Range: 1.4286. Min Range: -1.4286

Max Act: 0.8326. Min Act: -0.0000

Data Index: 1164122 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 1.4286. Min Range: -1.4286

Max Act: 0.8299. Min Act: -0.0000

Data Index: 1644696 (Python Code)

Max Activating Token Index: 962

Text #19

Max Range: 1.4286. Min Range: -1.4286

Max Act: 0.8787. Min Act: -0.0000

Data Index: 1469882 (Python Code)

Max Activating Token Index: 803