Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1845 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.8255. Min Range: -4.8255
Max Act: 4.8255. Min Act: -0.1700
Data Index: 1416119 (Python Code)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8255. Min Range: -4.8255
Max Act: 4.8255. Min Act: -0.1700
Data Index: 1528619 (Python Code)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8255. Min Range: -4.8255
Max Act: 4.7630. Min Act: -0.1700
Data Index: 1557361 (Python Code)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8255. Min Range: -4.8255
Max Act: 4.7005. Min Act: -0.1700
Data Index: 1631364 (Python Code)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8255. Min Range: -4.8255
Max Act: 4.7317. Min Act: -0.1700
Data Index: 1394234 (Python Code)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8255. Min Range: -4.8255
Max Act: 4.7317. Min Act: -0.1700
Data Index: 1515488 (Python Code)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8255. Min Range: -4.8255
Max Act: 4.6380. Min Act: -0.1700
Data Index: 1500773 (Python Code)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8255. Min Range: -4.8255
Max Act: 4.6692. Min Act: -0.1700
Data Index: 1534876 (Python Code)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8255. Min Range: -4.8255
Max Act: 4.6067. Min Act: -0.1700
Data Index: 1512189 (Python Code)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8255. Min Range: -4.8255
Max Act: 4.5755. Min Act: -0.1700
Data Index: 1484639 (Python Code)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8255. Min Range: -4.8255
Max Act: 4.6067. Min Act: -0.1700
Data Index: 1556002 (Python Code)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8255. Min Range: -4.8255
Max Act: 4.6380. Min Act: -0.1700
Data Index: 1434082 (Python Code)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8255. Min Range: -4.8255
Max Act: 4.6380. Min Act: -0.1700
Data Index: 1616301 (Python Code)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8255. Min Range: -4.8255
Max Act: 4.6067. Min Act: -0.1700
Data Index: 1364462 (Python Code)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8255. Min Range: -4.8255
Max Act: 4.6067. Min Act: -0.1700
Data Index: 1540559 (Python Code)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8255. Min Range: -4.8255
Max Act: 4.5755. Min Act: -0.1700
Data Index: 1563482 (Python Code)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8255. Min Range: -4.8255
Max Act: 4.5755. Min Act: -0.1700
Data Index: 1625016 (Python Code)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8255. Min Range: -4.8255
Max Act: 4.5755. Min Act: -0.1700
Data Index: 1367115 (Python Code)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8255. Min Range: -4.8255
Max Act: 4.5755. Min Act: -0.1700
Data Index: 1582645 (Python Code)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8255. Min Range: -4.8255
Max Act: 4.6067. Min Act: -0.1700
Data Index: 1434452 (Python Code)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19