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

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

Neuron 4033 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: 2.9291. Min Range: -2.9291

Max Act: 2.9291. Min Act: -0.0000

Data Index: 1426099 (Python Code)

Max Activating Token Index: 505

Text #1

Max Range: 2.9291. Min Range: -2.9291

Max Act: 2.7064. Min Act: -0.0000

Data Index: 1530779 (Python Code)

Max Activating Token Index: 609

Text #2

Max Range: 2.9291. Min Range: -2.9291

Max Act: 2.5533. Min Act: -0.0000

Data Index: 1619457 (Python Code)

Max Activating Token Index: 370

Text #3

Max Range: 2.9291. Min Range: -2.9291

Max Act: 2.3831. Min Act: -0.0000

Data Index: 1611241 (Python Code)

Max Activating Token Index: 372

Text #4

Max Range: 2.9291. Min Range: -2.9291

Max Act: 2.3059. Min Act: -0.0000

Data Index: 1475905 (Python Code)

Max Activating Token Index: 414

Text #5

Max Range: 2.9291. Min Range: -2.9291

Max Act: 2.3765. Min Act: -0.0000

Data Index: 1415145 (Python Code)

Max Activating Token Index: 776

Text #6

Max Range: 2.9291. Min Range: -2.9291

Max Act: 2.3717. Min Act: -0.0000

Data Index: 1483277 (Python Code)

Max Activating Token Index: 751

Text #7

Max Range: 2.9291. Min Range: -2.9291

Max Act: 2.3416. Min Act: -0.0000

Data Index: 1436030 (Python Code)

Max Activating Token Index: 793

Text #8

Max Range: 2.9291. Min Range: -2.9291

Max Act: 2.3585. Min Act: -0.0000

Data Index: 1474869 (Python Code)

Max Activating Token Index: 257

Text #9

Max Range: 2.9291. Min Range: -2.9291

Max Act: 2.2325. Min Act: -0.0000

Data Index: 1591639 (Python Code)

Max Activating Token Index: 275

Text #10

Max Range: 2.9291. Min Range: -2.9291

Max Act: 2.3244. Min Act: -0.0000

Data Index: 1398798 (Python Code)

Max Activating Token Index: 596

Text #11

Max Range: 2.9291. Min Range: -2.9291

Max Act: 2.3179. Min Act: -0.0000

Data Index: 1561770 (Python Code)

Max Activating Token Index: 21

Text #12

Max Range: 2.9291. Min Range: -2.9291

Max Act: 2.4064. Min Act: -0.0000

Data Index: 1586027 (Python Code)

Max Activating Token Index: 494

Text #13

Max Range: 2.9291. Min Range: -2.9291

Max Act: 2.1915. Min Act: -0.0000

Data Index: 1418002 (Python Code)

Max Activating Token Index: 22

Text #14

Max Range: 2.9291. Min Range: -2.9291

Max Act: 2.2498. Min Act: -0.0000

Data Index: 1463937 (Python Code)

Max Activating Token Index: 426

Text #15

Max Range: 2.9291. Min Range: -2.9291

Max Act: 2.2155. Min Act: -0.0000

Data Index: 1426219 (Python Code)

Max Activating Token Index: 745

Text #16

Max Range: 2.9291. Min Range: -2.9291

Max Act: 2.1905. Min Act: -0.0000

Data Index: 1421175 (Python Code)

Max Activating Token Index: 243

Text #17

Max Range: 2.9291. Min Range: -2.9291

Max Act: 2.0170. Min Act: -0.0000

Data Index: 1367226 (Python Code)

Max Activating Token Index: 194

Text #18

Max Range: 2.9291. Min Range: -2.9291

Max Act: 2.1143. Min Act: -0.0000

Data Index: 1459991 (Python Code)

Max Activating Token Index: 192

Text #19

Max Range: 2.9291. Min Range: -2.9291

Max Act: 2.2270. Min Act: -0.0000

Data Index: 1519754 (Python Code)

Max Activating Token Index: 683