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

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

Neuron 2504 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4168. Min Range: -1.4168

Max Act: 1.4168. Min Act: -0.0001

Data Index: 1604562 (Python Code)

Max Activating Token Index: 928

Text #1

Max Range: 1.4168. Min Range: -1.4168

Max Act: 1.3108. Min Act: -0.0000

Data Index: 1470027 (Python Code)

Max Activating Token Index: 698

Text #2

Max Range: 1.4168. Min Range: -1.4168

Max Act: 1.2285. Min Act: -0.0001

Data Index: 1633658 (Python Code)

Max Activating Token Index: 766

Text #3

Max Range: 1.4168. Min Range: -1.4168

Max Act: 1.2641. Min Act: -0.0000

Data Index: 198775 (C4 (Web Text))

Max Activating Token Index: 1013

Text #4

Max Range: 1.4168. Min Range: -1.4168

Max Act: 1.1763. Min Act: -0.0000

Data Index: 1103848 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 1.4168. Min Range: -1.4168

Max Act: 1.2801. Min Act: -0.0000

Data Index: 1360802 (Python Code)

Max Activating Token Index: 99

Text #6

Max Range: 1.4168. Min Range: -1.4168

Max Act: 1.2255. Min Act: -0.0000

Data Index: 750067 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 1.4168. Min Range: -1.4168

Max Act: 1.1323. Min Act: -0.0000

Data Index: 1478073 (Python Code)

Max Activating Token Index: 681

Text #8

Max Range: 1.4168. Min Range: -1.4168

Max Act: 1.1957. Min Act: -0.0000

Data Index: 875037 (C4 (Web Text))

Max Activating Token Index: 708

Text #9

Max Range: 1.4168. Min Range: -1.4168

Max Act: 1.1678. Min Act: -0.0000

Data Index: 669582 (C4 (Web Text))

Max Activating Token Index: 806

Text #10

Max Range: 1.4168. Min Range: -1.4168

Max Act: 1.2401. Min Act: -0.0001

Data Index: 1488393 (Python Code)

Max Activating Token Index: 441

Text #11

Max Range: 1.4168. Min Range: -1.4168

Max Act: 1.1192. Min Act: -0.0000

Data Index: 1386460 (Python Code)

Max Activating Token Index: 258

Text #12

Max Range: 1.4168. Min Range: -1.4168

Max Act: 1.1208. Min Act: -0.0000

Data Index: 254776 (C4 (Web Text))

Max Activating Token Index: 206

Text #13

Max Range: 1.4168. Min Range: -1.4168

Max Act: 1.1124. Min Act: -0.0000

Data Index: 1471694 (Python Code)

Max Activating Token Index: 777

Text #14

Max Range: 1.4168. Min Range: -1.4168

Max Act: 1.1331. Min Act: -0.0000

Data Index: 132034 (C4 (Web Text))

Max Activating Token Index: 577

Text #15

Max Range: 1.4168. Min Range: -1.4168

Max Act: 1.1213. Min Act: -0.0000

Data Index: 217493 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 1.4168. Min Range: -1.4168

Max Act: 1.0881. Min Act: -0.0000

Data Index: 851282 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 1.4168. Min Range: -1.4168

Max Act: 1.1111. Min Act: -0.0000

Data Index: 254237 (C4 (Web Text))

Max Activating Token Index: 995

Text #18

Max Range: 1.4168. Min Range: -1.4168

Max Act: 1.0802. Min Act: -0.0000

Data Index: 72239 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 1.4168. Min Range: -1.4168

Max Act: 1.1188. Min Act: -0.0000

Data Index: 1522761 (Python Code)

Max Activating Token Index: 843