Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 897 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.9182. Min Act: 0.0001

Data Index: 1377246 (Python Code)

Max Activating Token Index: 77

Text #1

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.9268. Min Act: -0.0000

Data Index: 1538074 (Python Code)

Max Activating Token Index: 49

Text #2

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.9029. Min Act: -0.0000

Data Index: 1649738 (Python Code)

Max Activating Token Index: 218

Text #3

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.8811. Min Act: 0.0001

Data Index: 1507274 (Python Code)

Max Activating Token Index: 209

Text #4

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.8100. Min Act: 0.0001

Data Index: 1447839 (Python Code)

Max Activating Token Index: 872

Text #5

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.7598. Min Act: 0.0001

Data Index: 1424252 (Python Code)

Max Activating Token Index: 23

Text #6

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.7413. Min Act: 0.0001

Data Index: 1623417 (Python Code)

Max Activating Token Index: 94

Text #7

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.7066. Min Act: -0.0000

Data Index: 1481001 (Python Code)

Max Activating Token Index: 497

Text #8

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.6846. Min Act: 0.0000

Data Index: 1509055 (Python Code)

Max Activating Token Index: 904

Text #9

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.6737. Min Act: 0.0001

Data Index: 1426910 (Python Code)

Max Activating Token Index: 213

Text #10

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.6463. Min Act: 0.0001

Data Index: 1548619 (Python Code)

Max Activating Token Index: 28

Text #11

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.6502. Min Act: -0.0000

Data Index: 1380547 (Python Code)

Max Activating Token Index: 205

Text #12

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.6338. Min Act: -0.0000

Data Index: 1511063 (Python Code)

Max Activating Token Index: 901

Text #13

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.6230. Min Act: -0.0000

Data Index: 1457111 (Python Code)

Max Activating Token Index: 568

Text #14

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.6712. Min Act: -0.0000

Data Index: 1528683 (Python Code)

Max Activating Token Index: 861

Text #15

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.6202. Min Act: 0.0001

Data Index: 1524639 (Python Code)

Max Activating Token Index: 41

Text #16

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.6109. Min Act: 0.0001

Data Index: 1577225 (Python Code)

Max Activating Token Index: 504

Text #17

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.6148. Min Act: 0.0000

Data Index: 1459626 (Python Code)

Max Activating Token Index: 274

Text #18

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.6013. Min Act: 0.0001

Data Index: 1507908 (Python Code)

Max Activating Token Index: 166

Text #19

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.5833. Min Act: 0.0001

Data Index: 1545638 (Python Code)

Max Activating Token Index: 582