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

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

Neuron 2444 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2645. Min Act: -0.0000

Data Index: 1178556 (C4 (Web Text))

Max Activating Token Index: 574

Text #1

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2491. Min Act: -0.0000

Data Index: 640857 (C4 (Web Text))

Max Activating Token Index: 402

Text #2

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2475. Min Act: -0.0000

Data Index: 188155 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2419. Min Act: -0.0000

Data Index: 171764 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2392. Min Act: -0.0000

Data Index: 971161 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2357. Min Act: -0.0000

Data Index: 573897 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2272. Min Act: -0.0000

Data Index: 510101 (C4 (Web Text))

Max Activating Token Index: 308

Text #7

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2244. Min Act: -0.0000

Data Index: 756704 (C4 (Web Text))

Max Activating Token Index: 587

Text #8

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2256. Min Act: -0.0000

Data Index: 9023 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2235. Min Act: -0.0000

Data Index: 354955 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2361. Min Act: -0.0000

Data Index: 822253 (C4 (Web Text))

Max Activating Token Index: 648

Text #11

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2281. Min Act: -0.0000

Data Index: 448737 (C4 (Web Text))

Max Activating Token Index: 921

Text #12

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2091. Min Act: -0.0000

Data Index: 448996 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2272. Min Act: -0.0000

Data Index: 464568 (C4 (Web Text))

Max Activating Token Index: 897

Text #14

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2182. Min Act: -0.0000

Data Index: 841786 (C4 (Web Text))

Max Activating Token Index: 882

Text #15

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2150. Min Act: -0.0000

Data Index: 869372 (C4 (Web Text))

Max Activating Token Index: 304

Text #16

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2125. Min Act: -0.0000

Data Index: 1082647 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2197. Min Act: -0.0000

Data Index: 452878 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2034. Min Act: -0.0000

Data Index: 215390 (C4 (Web Text))

Max Activating Token Index: 1020

Text #19

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2131. Min Act: -0.0000

Data Index: 381584 (C4 (Web Text))

Max Activating Token Index: 722