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

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

Neuron 5719 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6974. Min Act: -0.0000

Data Index: 1473971 (Python Code)

Max Activating Token Index: 342

Text #1

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.7884. Min Act: -0.0000

Data Index: 1511308 (Python Code)

Max Activating Token Index: 822

Text #2

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.7198. Min Act: -0.0000

Data Index: 1537992 (Python Code)

Max Activating Token Index: 529

Text #3

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6799. Min Act: -0.0000

Data Index: 1648646 (Python Code)

Max Activating Token Index: 79

Text #4

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6723. Min Act: -0.0000

Data Index: 1518080 (Python Code)

Max Activating Token Index: 849

Text #5

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6363. Min Act: -0.0000

Data Index: 1637530 (Python Code)

Max Activating Token Index: 53

Text #6

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6386. Min Act: -0.0000

Data Index: 1607740 (Python Code)

Max Activating Token Index: 829

Text #7

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6543. Min Act: -0.0000

Data Index: 1435271 (Python Code)

Max Activating Token Index: 546

Text #8

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6321. Min Act: -0.0000

Data Index: 1524655 (Python Code)

Max Activating Token Index: 82

Text #9

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.5938. Min Act: -0.0000

Data Index: 1539359 (Python Code)

Max Activating Token Index: 216

Text #10

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.5967. Min Act: -0.0000

Data Index: 1518942 (Python Code)

Max Activating Token Index: 132

Text #11

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.5762. Min Act: -0.0000

Data Index: 1388088 (Python Code)

Max Activating Token Index: 817

Text #12

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6093. Min Act: -0.0000

Data Index: 1375471 (Python Code)

Max Activating Token Index: 17

Text #13

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6261. Min Act: -0.0000

Data Index: 1460071 (Python Code)

Max Activating Token Index: 47

Text #14

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6101. Min Act: -0.0000

Data Index: 1362244 (Python Code)

Max Activating Token Index: 904

Text #15

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6274. Min Act: -0.0000

Data Index: 1425658 (Python Code)

Max Activating Token Index: 146

Text #16

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6009. Min Act: -0.0000

Data Index: 1620987 (Python Code)

Max Activating Token Index: 119

Text #17

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6171. Min Act: -0.0000

Data Index: 1547223 (Python Code)

Max Activating Token Index: 474

Text #18

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.5656. Min Act: -0.0000

Data Index: 1438949 (Python Code)

Max Activating Token Index: 864

Text #19

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.5996. Min Act: -0.0000

Data Index: 1449163 (Python Code)

Max Activating Token Index: 900