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

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

Neuron 3480 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.8101. Min Act: -0.0000

Data Index: 1618284 (Python Code)

Max Activating Token Index: 136

Text #1

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.7371. Min Act: -0.0000

Data Index: 1561853 (Python Code)

Max Activating Token Index: 75

Text #2

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.7013. Min Act: -0.0000

Data Index: 1461184 (Python Code)

Max Activating Token Index: 25

Text #3

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6307. Min Act: -0.0000

Data Index: 1373246 (Python Code)

Max Activating Token Index: 67

Text #4

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6569. Min Act: -0.0000

Data Index: 1421349 (Python Code)

Max Activating Token Index: 67

Text #5

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6818. Min Act: -0.0000

Data Index: 1513515 (Python Code)

Max Activating Token Index: 81

Text #6

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6283. Min Act: -0.0000

Data Index: 1530032 (Python Code)

Max Activating Token Index: 21

Text #7

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6268. Min Act: -0.0000

Data Index: 1469978 (Python Code)

Max Activating Token Index: 35

Text #8

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6669. Min Act: -0.0000

Data Index: 1543877 (Python Code)

Max Activating Token Index: 109

Text #9

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6613. Min Act: -0.0000

Data Index: 1572431 (Python Code)

Max Activating Token Index: 88

Text #10

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6210. Min Act: 0.0000

Data Index: 1457730 (Python Code)

Max Activating Token Index: 72

Text #11

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6475. Min Act: -0.0000

Data Index: 1499105 (Python Code)

Max Activating Token Index: 27

Text #12

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.5898. Min Act: -0.0000

Data Index: 1539914 (Python Code)

Max Activating Token Index: 175

Text #13

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6308. Min Act: 0.0000

Data Index: 1390190 (Python Code)

Max Activating Token Index: 284

Text #14

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.5684. Min Act: -0.0000

Data Index: 1589222 (Python Code)

Max Activating Token Index: 866

Text #15

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.5930. Min Act: -0.0000

Data Index: 1613070 (Python Code)

Max Activating Token Index: 25

Text #16

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.5937. Min Act: -0.0000

Data Index: 1504864 (Python Code)

Max Activating Token Index: 119

Text #17

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.5902. Min Act: 0.0000

Data Index: 1626059 (Python Code)

Max Activating Token Index: 144

Text #18

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.5939. Min Act: -0.0000

Data Index: 1406843 (Python Code)

Max Activating Token Index: 122

Text #19

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.5942. Min Act: -0.0000

Data Index: 1498181 (Python Code)

Max Activating Token Index: 61