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

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

Neuron 1744 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0343. Min Act: -0.0002

Data Index: 1385602 (Python Code)

Max Activating Token Index: 306

Text #1

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0349. Min Act: -0.0002

Data Index: 1599045 (Python Code)

Max Activating Token Index: 149

Text #2

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0322. Min Act: -0.0002

Data Index: 1601325 (Python Code)

Max Activating Token Index: 990

Text #3

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0321. Min Act: -0.0002

Data Index: 891292 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0315. Min Act: -0.0002

Data Index: 1621693 (Python Code)

Max Activating Token Index: 536

Text #5

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0310. Min Act: -0.0002

Data Index: 1161323 (C4 (Web Text))

Max Activating Token Index: 366

Text #6

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0310. Min Act: -0.0002

Data Index: 1600356 (Python Code)

Max Activating Token Index: 972

Text #7

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0305. Min Act: -0.0002

Data Index: 869053 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0299. Min Act: -0.0002

Data Index: 545025 (C4 (Web Text))

Max Activating Token Index: 937

Text #9

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0311. Min Act: -0.0002

Data Index: 352126 (C4 (Web Text))

Max Activating Token Index: 330

Text #10

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0293. Min Act: -0.0002

Data Index: 1400564 (Python Code)

Max Activating Token Index: 96

Text #11

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0292. Min Act: -0.0002

Data Index: 1324174 (C4 (Web Text))

Max Activating Token Index: 687

Text #12

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0294. Min Act: -0.0002

Data Index: 272228 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0280. Min Act: -0.0002

Data Index: 1074579 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0277. Min Act: -0.0002

Data Index: 773491 (C4 (Web Text))

Max Activating Token Index: 869

Text #15

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0279. Min Act: -0.0002

Data Index: 905257 (C4 (Web Text))

Max Activating Token Index: 679

Text #16

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0283. Min Act: -0.0002

Data Index: 1529806 (Python Code)

Max Activating Token Index: 127

Text #17

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0275. Min Act: -0.0002

Data Index: 959373 (C4 (Web Text))

Max Activating Token Index: 162

Text #18

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0274. Min Act: -0.0002

Data Index: 425858 (C4 (Web Text))

Max Activating Token Index: 305

Text #19

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0265. Min Act: -0.0002

Data Index: 1042295 (C4 (Web Text))

Max Activating Token Index: 288