Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 148 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 1.7789. Min Range: -1.7789
Max Act: 1.7789. Min Act: -0.1700
Data Index: 998492 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7789. Min Range: -1.7789
Max Act: 1.7184. Min Act: -0.1700
Data Index: 1589417 (Python Code)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7789. Min Range: -1.7789
Max Act: 1.6751. Min Act: -0.1700
Data Index: 997504 (C4 (Web Text))
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7789. Min Range: -1.7789
Max Act: 1.6403. Min Act: -0.1700
Data Index: 1645900 (Python Code)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7789. Min Range: -1.7789
Max Act: 1.6316. Min Act: -0.1699
Data Index: 1544890 (Python Code)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7789. Min Range: -1.7789
Max Act: 1.6229. Min Act: -0.1699
Data Index: 1361803 (Python Code)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7789. Min Range: -1.7789
Max Act: 1.5967. Min Act: -0.1700
Data Index: 1432503 (Python Code)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7789. Min Range: -1.7789
Max Act: 1.6055. Min Act: -0.1700
Data Index: 1520730 (Python Code)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7789. Min Range: -1.7789
Max Act: 1.5880. Min Act: -0.1700
Data Index: 1576744 (Python Code)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7789. Min Range: -1.7789
Max Act: 1.5793. Min Act: -0.1700
Data Index: 484607 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7789. Min Range: -1.7789
Max Act: 1.5793. Min Act: -0.1699
Data Index: 677038 (C4 (Web Text))
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7789. Min Range: -1.7789
Max Act: 1.5705. Min Act: -0.1700
Data Index: 1637085 (Python Code)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7789. Min Range: -1.7789
Max Act: 1.5618. Min Act: -0.1700
Data Index: 327718 (C4 (Web Text))
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7789. Min Range: -1.7789
Max Act: 1.5618. Min Act: -0.1700
Data Index: 1507790 (Python Code)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7789. Min Range: -1.7789
Max Act: 1.5618. Min Act: -0.1700
Data Index: 1478004 (Python Code)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7789. Min Range: -1.7789
Max Act: 1.5530. Min Act: -0.1699
Data Index: 1476083 (Python Code)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7789. Min Range: -1.7789
Max Act: 1.5618. Min Act: -0.1700
Data Index: 1498846 (Python Code)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7789. Min Range: -1.7789
Max Act: 1.5618. Min Act: -0.1699
Data Index: 1527136 (Python Code)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7789. Min Range: -1.7789
Max Act: 1.5530. Min Act: -0.1700
Data Index: 1614869 (Python Code)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7789. Min Range: -1.7789
Max Act: 1.5530. Min Act: -0.1699
Data Index: 905635 (C4 (Web Text))
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #19