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

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

Neuron 4442 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0187. Min Range: -1.0187

Max Act: 1.0187. Min Act: -0.0001

Data Index: 360546 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.9512. Min Act: -0.0001

Data Index: 879320 (C4 (Web Text))

Max Activating Token Index: 797

Text #2

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.9647. Min Act: -0.0001

Data Index: 1641965 (Python Code)

Max Activating Token Index: 522

Text #3

Max Range: 1.0187. Min Range: -1.0187

Max Act: 1.0038. Min Act: -0.0001

Data Index: 1482150 (Python Code)

Max Activating Token Index: 467

Text #4

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.9683. Min Act: -0.0001

Data Index: 1368458 (Python Code)

Max Activating Token Index: 14

Text #5

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.9345. Min Act: -0.0000

Data Index: 1649399 (Python Code)

Max Activating Token Index: 631

Text #6

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.9180. Min Act: -0.0001

Data Index: 1556036 (Python Code)

Max Activating Token Index: 700

Text #7

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.9251. Min Act: -0.0000

Data Index: 1376613 (Python Code)

Max Activating Token Index: 63

Text #8

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.9441. Min Act: -0.0001

Data Index: 1418362 (Python Code)

Max Activating Token Index: 51

Text #9

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.8394. Min Act: -0.0001

Data Index: 1364559 (Python Code)

Max Activating Token Index: 320

Text #10

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.9155. Min Act: -0.0001

Data Index: 1648759 (Python Code)

Max Activating Token Index: 280

Text #11

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.8909. Min Act: -0.0001

Data Index: 1613069 (Python Code)

Max Activating Token Index: 521

Text #12

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.8500. Min Act: -0.0001

Data Index: 51929 (C4 (Web Text))

Max Activating Token Index: 107

Text #13

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.8770. Min Act: -0.0001

Data Index: 1366138 (Python Code)

Max Activating Token Index: 206

Text #14

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.8402. Min Act: -0.0001

Data Index: 1507539 (Python Code)

Max Activating Token Index: 292

Text #15

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.7962. Min Act: -0.0000

Data Index: 1451304 (Python Code)

Max Activating Token Index: 346

Text #16

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.9491. Min Act: -0.0001

Data Index: 618338 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.8707. Min Act: -0.0001

Data Index: 411045 (C4 (Web Text))

Max Activating Token Index: 75

Text #18

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.8062. Min Act: -0.0001

Data Index: 954879 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.8206. Min Act: -0.0001

Data Index: 1643224 (Python Code)

Max Activating Token Index: 457