Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 630 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6996. Min Range: -8.6996
Max Act: 8.6996. Min Act: -0.1700
Data Index: 6549939 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6996. Min Range: -8.6996
Max Act: 8.6371. Min Act: -0.1700
Data Index: 4155803 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6996. Min Range: -8.6996
Max Act: 8.5746. Min Act: -0.1700
Data Index: 4543851 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6996. Min Range: -8.6996
Max Act: 8.5121. Min Act: -0.1700
Data Index: 4767105 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6996. Min Range: -8.6996
Max Act: 8.3871. Min Act: -0.1700
Data Index: 1463966 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6996. Min Range: -8.6996
Max Act: 8.3871. Min Act: -0.1700
Data Index: 3365166 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6996. Min Range: -8.6996
Max Act: 8.1996. Min Act: -0.1700
Data Index: 5014566 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6996. Min Range: -8.6996
Max Act: 8.1996. Min Act: -0.1700
Data Index: 5555638 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6996. Min Range: -8.6996
Max Act: 8.1996. Min Act: -0.1700
Data Index: 1592520 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6996. Min Range: -8.6996
Max Act: 8.1371. Min Act: -0.1700
Data Index: 1202985 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6996. Min Range: -8.6996
Max Act: 8.0746. Min Act: -0.1700
Data Index: 3470666 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6996. Min Range: -8.6996
Max Act: 8.0746. Min Act: -0.1700
Data Index: 131734 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6996. Min Range: -8.6996
Max Act: 8.0121. Min Act: -0.1700
Data Index: 3736376 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6996. Min Range: -8.6996
Max Act: 8.0121. Min Act: -0.1700
Data Index: 593782 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6996. Min Range: -8.6996
Max Act: 8.0121. Min Act: -0.1700
Data Index: 4599842 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6996. Min Range: -8.6996
Max Act: 8.0121. Min Act: -0.1700
Data Index: 1376412 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6996. Min Range: -8.6996
Max Act: 8.0121. Min Act: -0.1700
Data Index: 7631713 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6996. Min Range: -8.6996
Max Act: 7.9496. Min Act: -0.1700
Data Index: 4345953 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6996. Min Range: -8.6996
Max Act: 7.9496. Min Act: -0.1700
Data Index: 254651 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6996. Min Range: -8.6996
Max Act: 7.9496. Min Act: -0.1700
Data Index: 5331661 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19