Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3408 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5028. Min Range: -4.5028
Max Act: 4.5028. Min Act: -0.1700
Data Index: 4101480 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5028. Min Range: -4.5028
Max Act: 4.2840. Min Act: -0.1700
Data Index: 3321359 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5028. Min Range: -4.5028
Max Act: 4.2528. Min Act: -0.1700
Data Index: 3086885 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5028. Min Range: -4.5028
Max Act: 4.2528. Min Act: -0.1700
Data Index: 4369180 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5028. Min Range: -4.5028
Max Act: 4.1903. Min Act: -0.1700
Data Index: 3534414 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5028. Min Range: -4.5028
Max Act: 4.1590. Min Act: -0.1700
Data Index: 1366847 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5028. Min Range: -4.5028
Max Act: 4.1590. Min Act: -0.1700
Data Index: 1134476 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5028. Min Range: -4.5028
Max Act: 4.1278. Min Act: -0.1700
Data Index: 5204325 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5028. Min Range: -4.5028
Max Act: 4.1590. Min Act: -0.1700
Data Index: 6503900 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5028. Min Range: -4.5028
Max Act: 4.1278. Min Act: -0.1700
Data Index: 3777680 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5028. Min Range: -4.5028
Max Act: 4.1278. Min Act: -0.1700
Data Index: 219298 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5028. Min Range: -4.5028
Max Act: 4.1278. Min Act: -0.1700
Data Index: 4769692 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5028. Min Range: -4.5028
Max Act: 4.0965. Min Act: -0.1700
Data Index: 1780542 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5028. Min Range: -4.5028
Max Act: 4.0340. Min Act: -0.1700
Data Index: 3445133 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5028. Min Range: -4.5028
Max Act: 4.0340. Min Act: -0.1700
Data Index: 7664601 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5028. Min Range: -4.5028
Max Act: 3.9715. Min Act: -0.1700
Data Index: 6654189 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5028. Min Range: -4.5028
Max Act: 4.0027. Min Act: -0.1700
Data Index: 8584808 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5028. Min Range: -4.5028
Max Act: 4.0340. Min Act: -0.1700
Data Index: 3885017 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5028. Min Range: -4.5028
Max Act: 4.0027. Min Act: -0.1700
Data Index: 3588658 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5028. Min Range: -4.5028
Max Act: 4.0027. Min Act: -0.1700
Data Index: 2383398 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19