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

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

Neuron 3198 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: 2.7654. Min Range: -2.7654

Max Act: 2.7654. Min Act: -0.0000

Data Index: 352841 (C4 (Web Text))

Max Activating Token Index: 458

Text #1

Max Range: 2.7654. Min Range: -2.7654

Max Act: 2.6426. Min Act: -0.0000

Data Index: 688528 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 2.7654. Min Range: -2.7654

Max Act: 2.5162. Min Act: -0.0000

Data Index: 825797 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 2.7654. Min Range: -2.7654

Max Act: 2.6793. Min Act: -0.0000

Data Index: 182922 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 2.7654. Min Range: -2.7654

Max Act: 2.5235. Min Act: -0.0000

Data Index: 1120023 (C4 (Web Text))

Max Activating Token Index: 487

Text #5

Max Range: 2.7654. Min Range: -2.7654

Max Act: 2.2603. Min Act: -0.0000

Data Index: 521589 (C4 (Web Text))

Max Activating Token Index: 844

Text #6

Max Range: 2.7654. Min Range: -2.7654

Max Act: 2.5092. Min Act: -0.0000

Data Index: 966832 (C4 (Web Text))

Max Activating Token Index: 987

Text #7

Max Range: 2.7654. Min Range: -2.7654

Max Act: 2.1007. Min Act: -0.0000

Data Index: 468289 (C4 (Web Text))

Max Activating Token Index: 812

Text #8

Max Range: 2.7654. Min Range: -2.7654

Max Act: 2.3142. Min Act: -0.0000

Data Index: 127094 (C4 (Web Text))

Max Activating Token Index: 973

Text #9

Max Range: 2.7654. Min Range: -2.7654

Max Act: 2.3212. Min Act: -0.0000

Data Index: 919700 (C4 (Web Text))

Max Activating Token Index: 314

Text #10

Max Range: 2.7654. Min Range: -2.7654

Max Act: 2.3005. Min Act: -0.0000

Data Index: 514383 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 2.7654. Min Range: -2.7654

Max Act: 2.2731. Min Act: -0.0000

Data Index: 412869 (C4 (Web Text))

Max Activating Token Index: 232

Text #12

Max Range: 2.7654. Min Range: -2.7654

Max Act: 2.2439. Min Act: -0.0000

Data Index: 886881 (C4 (Web Text))

Max Activating Token Index: 565

Text #13

Max Range: 2.7654. Min Range: -2.7654

Max Act: 2.2098. Min Act: -0.0000

Data Index: 142529 (C4 (Web Text))

Max Activating Token Index: 1002

Text #14

Max Range: 2.7654. Min Range: -2.7654

Max Act: 2.2143. Min Act: -0.0000

Data Index: 1080906 (C4 (Web Text))

Max Activating Token Index: 502

Text #15

Max Range: 2.7654. Min Range: -2.7654

Max Act: 2.2088. Min Act: -0.0000

Data Index: 635508 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 2.7654. Min Range: -2.7654

Max Act: 1.9373. Min Act: -0.0000

Data Index: 557470 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 2.7654. Min Range: -2.7654

Max Act: 2.1260. Min Act: -0.0000

Data Index: 14180 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 2.7654. Min Range: -2.7654

Max Act: 1.9917. Min Act: -0.0000

Data Index: 884334 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 2.7654. Min Range: -2.7654

Max Act: 2.0259. Min Act: -0.0000

Data Index: 1148258 (C4 (Web Text))

Max Activating Token Index: 325