Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2008 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1077. Min Range: -1.1077

Max Act: 1.0779. Min Act: -0.0001

Data Index: 1481392 (Python Code)

Max Activating Token Index: 104

Text #1

Max Range: 1.1077. Min Range: -1.1077

Max Act: 1.0743. Min Act: -0.0001

Data Index: 1452742 (Python Code)

Max Activating Token Index: 18

Text #2

Max Range: 1.1077. Min Range: -1.1077

Max Act: 1.1077. Min Act: -0.0001

Data Index: 1419168 (Python Code)

Max Activating Token Index: 372

Text #3

Max Range: 1.1077. Min Range: -1.1077

Max Act: 1.0711. Min Act: -0.0001

Data Index: 1452136 (Python Code)

Max Activating Token Index: 391

Text #4

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.9853. Min Act: -0.0001

Data Index: 1519706 (Python Code)

Max Activating Token Index: 140

Text #5

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.9570. Min Act: -0.0001

Data Index: 1441149 (Python Code)

Max Activating Token Index: 659

Text #6

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.8907. Min Act: -0.0001

Data Index: 1432995 (Python Code)

Max Activating Token Index: 400

Text #7

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.9474. Min Act: -0.0001

Data Index: 1502872 (Python Code)

Max Activating Token Index: 646

Text #8

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.9350. Min Act: -0.0001

Data Index: 1492752 (Python Code)

Max Activating Token Index: 14

Text #9

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.9361. Min Act: -0.0001

Data Index: 1373004 (Python Code)

Max Activating Token Index: 927

Text #10

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.9327. Min Act: -0.0001

Data Index: 1523808 (Python Code)

Max Activating Token Index: 48

Text #11

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.9092. Min Act: -0.0001

Data Index: 1487383 (Python Code)

Max Activating Token Index: 939

Text #12

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.8756. Min Act: -0.0001

Data Index: 1527374 (Python Code)

Max Activating Token Index: 188

Text #13

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.9344. Min Act: -0.0001

Data Index: 1387932 (Python Code)

Max Activating Token Index: 319

Text #14

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.8486. Min Act: -0.0001

Data Index: 1549632 (Python Code)

Max Activating Token Index: 699

Text #15

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.9223. Min Act: -0.0001

Data Index: 1567871 (Python Code)

Max Activating Token Index: 696

Text #16

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.9169. Min Act: -0.0001

Data Index: 1458271 (Python Code)

Max Activating Token Index: 1004

Text #17

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.9205. Min Act: -0.0001

Data Index: 1530125 (Python Code)

Max Activating Token Index: 828

Text #18

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.9168. Min Act: -0.0001

Data Index: 1577428 (Python Code)

Max Activating Token Index: 393

Text #19

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.8765. Min Act: -0.0001

Data Index: 1635602 (Python Code)

Max Activating Token Index: 160