Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3276 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1502. Min Range: -9.1502
Max Act: 9.1502. Min Act: -0.1700
Data Index: 4548399 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1502. Min Range: -9.1502
Max Act: 9.0877. Min Act: -0.1700
Data Index: 1005330 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1502. Min Range: -9.1502
Max Act: 9.0877. Min Act: -0.1700
Data Index: 2847832 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1502. Min Range: -9.1502
Max Act: 8.8377. Min Act: -0.1700
Data Index: 2894969 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1502. Min Range: -9.1502
Max Act: 8.8377. Min Act: -0.1700
Data Index: 321139 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1502. Min Range: -9.1502
Max Act: 8.7752. Min Act: -0.1700
Data Index: 8094042 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1502. Min Range: -9.1502
Max Act: 8.7752. Min Act: -0.1700
Data Index: 1908046 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1502. Min Range: -9.1502
Max Act: 8.7127. Min Act: -0.1700
Data Index: 1479462 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1502. Min Range: -9.1502
Max Act: 8.7127. Min Act: -0.1700
Data Index: 5796348 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1502. Min Range: -9.1502
Max Act: 8.6502. Min Act: -0.1698
Data Index: 738551 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1502. Min Range: -9.1502
Max Act: 8.6502. Min Act: -0.1700
Data Index: 3036569 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1502. Min Range: -9.1502
Max Act: 8.6502. Min Act: -0.1700
Data Index: 6923642 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1502. Min Range: -9.1502
Max Act: 8.6502. Min Act: -0.1700
Data Index: 1188578 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1502. Min Range: -9.1502
Max Act: 8.6502. Min Act: -0.1700
Data Index: 7891406 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1502. Min Range: -9.1502
Max Act: 8.5877. Min Act: -0.1700
Data Index: 7200663 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1502. Min Range: -9.1502
Max Act: 8.5877. Min Act: -0.1700
Data Index: 8606469 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1502. Min Range: -9.1502
Max Act: 8.5877. Min Act: -0.1700
Data Index: 5669463 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1502. Min Range: -9.1502
Max Act: 8.5877. Min Act: -0.1700
Data Index: 4238276 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1502. Min Range: -9.1502
Max Act: 8.5877. Min Act: -0.1700
Data Index: 8428360 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1502. Min Range: -9.1502
Max Act: 8.5252. Min Act: -0.1700
Data Index: 7961063 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19