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

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

Neuron 3841 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4340. Min Range: -1.4340

Max Act: 1.4340. Min Act: -0.0001

Data Index: 244585 (C4 (Web Text))

Max Activating Token Index: 109

Text #1

Max Range: 1.4340. Min Range: -1.4340

Max Act: 1.2853. Min Act: -0.0000

Data Index: 171447 (C4 (Web Text))

Max Activating Token Index: 720

Text #2

Max Range: 1.4340. Min Range: -1.4340

Max Act: 1.2896. Min Act: -0.0000

Data Index: 608188 (C4 (Web Text))

Max Activating Token Index: 66

Text #3

Max Range: 1.4340. Min Range: -1.4340

Max Act: 1.3298. Min Act: -0.0000

Data Index: 1135552 (C4 (Web Text))

Max Activating Token Index: 844

Text #4

Max Range: 1.4340. Min Range: -1.4340

Max Act: 1.1906. Min Act: -0.0000

Data Index: 1481277 (Python Code)

Max Activating Token Index: 80

Text #5

Max Range: 1.4340. Min Range: -1.4340

Max Act: 1.2172. Min Act: -0.0000

Data Index: 1634024 (Python Code)

Max Activating Token Index: 346

Text #6

Max Range: 1.4340. Min Range: -1.4340

Max Act: 1.1603. Min Act: -0.0001

Data Index: 353663 (C4 (Web Text))

Max Activating Token Index: 498

Text #7

Max Range: 1.4340. Min Range: -1.4340

Max Act: 1.2163. Min Act: -0.0000

Data Index: 671554 (C4 (Web Text))

Max Activating Token Index: 759

Text #8

Max Range: 1.4340. Min Range: -1.4340

Max Act: 1.1600. Min Act: -0.0000

Data Index: 895328 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 1.4340. Min Range: -1.4340

Max Act: 1.2232. Min Act: -0.0000

Data Index: 1212346 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 1.4340. Min Range: -1.4340

Max Act: 1.1577. Min Act: -0.0000

Data Index: 1604244 (Python Code)

Max Activating Token Index: 692

Text #11

Max Range: 1.4340. Min Range: -1.4340

Max Act: 1.1204. Min Act: -0.0000

Data Index: 879239 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 1.4340. Min Range: -1.4340

Max Act: 1.1377. Min Act: -0.0000

Data Index: 48063 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 1.4340. Min Range: -1.4340

Max Act: 1.1402. Min Act: -0.0000

Data Index: 1368267 (Python Code)

Max Activating Token Index: 495

Text #14

Max Range: 1.4340. Min Range: -1.4340

Max Act: 1.0966. Min Act: -0.0000

Data Index: 986019 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 1.4340. Min Range: -1.4340

Max Act: 1.1210. Min Act: -0.0000

Data Index: 1374654 (Python Code)

Max Activating Token Index: 722

Text #16

Max Range: 1.4340. Min Range: -1.4340

Max Act: 1.0851. Min Act: -0.0000

Data Index: 751048 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 1.4340. Min Range: -1.4340

Max Act: 1.0883. Min Act: -0.0000

Data Index: 1146712 (C4 (Web Text))

Max Activating Token Index: 904

Text #18

Max Range: 1.4340. Min Range: -1.4340

Max Act: 1.1235. Min Act: -0.0000

Data Index: 678123 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 1.4340. Min Range: -1.4340

Max Act: 1.1166. Min Act: -0.0001

Data Index: 1228293 (C4 (Web Text))

Max Activating Token Index: 777