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

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

Neuron 4015 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0206. Min Range: -1.0206

Max Act: 1.0206. Min Act: -0.0001

Data Index: 1421444 (Python Code)

Max Activating Token Index: 773

Text #1

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.9563. Min Act: -0.0001

Data Index: 1491326 (Python Code)

Max Activating Token Index: 755

Text #2

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.9548. Min Act: -0.0000

Data Index: 1459939 (Python Code)

Max Activating Token Index: 65

Text #3

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.9361. Min Act: -0.0001

Data Index: 1565078 (Python Code)

Max Activating Token Index: 279

Text #4

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.9247. Min Act: -0.0001

Data Index: 1603865 (Python Code)

Max Activating Token Index: 63

Text #5

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.8781. Min Act: -0.0000

Data Index: 1470566 (Python Code)

Max Activating Token Index: 284

Text #6

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.8768. Min Act: -0.0001

Data Index: 1515388 (Python Code)

Max Activating Token Index: 247

Text #7

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.8172. Min Act: -0.0001

Data Index: 1603019 (Python Code)

Max Activating Token Index: 746

Text #8

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.8313. Min Act: -0.0000

Data Index: 1579939 (Python Code)

Max Activating Token Index: 137

Text #9

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.8815. Min Act: -0.0001

Data Index: 1486601 (Python Code)

Max Activating Token Index: 52

Text #10

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.8837. Min Act: -0.0001

Data Index: 1644635 (Python Code)

Max Activating Token Index: 887

Text #11

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.8648. Min Act: -0.0001

Data Index: 1440925 (Python Code)

Max Activating Token Index: 551

Text #12

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.8180. Min Act: -0.0000

Data Index: 1476309 (Python Code)

Max Activating Token Index: 159

Text #13

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.8115. Min Act: -0.0001

Data Index: 1360981 (Python Code)

Max Activating Token Index: 202

Text #14

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.8383. Min Act: -0.0001

Data Index: 1476475 (Python Code)

Max Activating Token Index: 49

Text #15

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.8040. Min Act: -0.0001

Data Index: 1539175 (Python Code)

Max Activating Token Index: 89

Text #16

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.7671. Min Act: -0.0001

Data Index: 1432135 (Python Code)

Max Activating Token Index: 994

Text #17

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.7865. Min Act: -0.0001

Data Index: 1380233 (Python Code)

Max Activating Token Index: 302

Text #18

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.7862. Min Act: -0.0000

Data Index: 1493568 (Python Code)

Max Activating Token Index: 991

Text #19

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.7451. Min Act: -0.0000

Data Index: 1599200 (Python Code)

Max Activating Token Index: 1002