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

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

Neuron 2109 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3784. Min Range: -2.3784

Max Act: 2.3784. Min Act: -0.0000

Data Index: 971533 (C4 (Web Text))

Max Activating Token Index: 655

Text #1

Max Range: 2.3784. Min Range: -2.3784

Max Act: 2.2260. Min Act: -0.0000

Data Index: 899285 (C4 (Web Text))

Max Activating Token Index: 304

Text #2

Max Range: 2.3784. Min Range: -2.3784

Max Act: 1.8859. Min Act: -0.0000

Data Index: 243453 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 2.3784. Min Range: -2.3784

Max Act: 1.8126. Min Act: -0.0000

Data Index: 1277777 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 2.3784. Min Range: -2.3784

Max Act: 1.8741. Min Act: -0.0000

Data Index: 1231288 (C4 (Web Text))

Max Activating Token Index: 142

Text #5

Max Range: 2.3784. Min Range: -2.3784

Max Act: 1.7861. Min Act: -0.0000

Data Index: 688705 (C4 (Web Text))

Max Activating Token Index: 657

Text #6

Max Range: 2.3784. Min Range: -2.3784

Max Act: 1.8247. Min Act: -0.0000

Data Index: 404111 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 2.3784. Min Range: -2.3784

Max Act: 1.7893. Min Act: -0.0000

Data Index: 747889 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 2.3784. Min Range: -2.3784

Max Act: 1.5930. Min Act: -0.0000

Data Index: 979364 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 2.3784. Min Range: -2.3784

Max Act: 1.7513. Min Act: -0.0000

Data Index: 98608 (C4 (Web Text))

Max Activating Token Index: 965

Text #10

Max Range: 2.3784. Min Range: -2.3784

Max Act: 1.8278. Min Act: -0.0000

Data Index: 485942 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 2.3784. Min Range: -2.3784

Max Act: 1.6172. Min Act: -0.0000

Data Index: 890833 (C4 (Web Text))

Max Activating Token Index: 549

Text #12

Max Range: 2.3784. Min Range: -2.3784

Max Act: 1.6073. Min Act: -0.0000

Data Index: 1065019 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 2.3784. Min Range: -2.3784

Max Act: 1.5797. Min Act: -0.0000

Data Index: 158791 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 2.3784. Min Range: -2.3784

Max Act: 1.4824. Min Act: -0.0000

Data Index: 705587 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 2.3784. Min Range: -2.3784

Max Act: 1.5526. Min Act: -0.0000

Data Index: 404536 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 2.3784. Min Range: -2.3784

Max Act: 1.4291. Min Act: -0.0000

Data Index: 28699 (C4 (Web Text))

Max Activating Token Index: 76

Text #17

Max Range: 2.3784. Min Range: -2.3784

Max Act: 1.4320. Min Act: -0.0000

Data Index: 27452 (C4 (Web Text))

Max Activating Token Index: 342

Text #18

Max Range: 2.3784. Min Range: -2.3784

Max Act: 1.5270. Min Act: -0.0000

Data Index: 872282 (C4 (Web Text))

Max Activating Token Index: 420

Text #19

Max Range: 2.3784. Min Range: -2.3784

Max Act: 1.5224. Min Act: -0.0000

Data Index: 1253124 (C4 (Web Text))

Max Activating Token Index: 535