Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3510 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1203. Min Range: -6.1203
Max Act: 6.1203. Min Act: -0.1700
Data Index: 3190204 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1203. Min Range: -6.1203
Max Act: 5.9953. Min Act: -0.1700
Data Index: 5529613 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1203. Min Range: -6.1203
Max Act: 5.9640. Min Act: -0.1700
Data Index: 8744638 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1203. Min Range: -6.1203
Max Act: 5.9640. Min Act: -0.1700
Data Index: 4781934 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1203. Min Range: -6.1203
Max Act: 5.9640. Min Act: -0.1700
Data Index: 6106735 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1203. Min Range: -6.1203
Max Act: 5.9328. Min Act: -0.1700
Data Index: 8175315 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1203. Min Range: -6.1203
Max Act: 5.8703. Min Act: -0.1700
Data Index: 1493797 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1203. Min Range: -6.1203
Max Act: 5.9015. Min Act: -0.1700
Data Index: 979739 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1203. Min Range: -6.1203
Max Act: 5.9015. Min Act: -0.1700
Data Index: 6928267 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1203. Min Range: -6.1203
Max Act: 5.8703. Min Act: -0.1700
Data Index: 82502 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1203. Min Range: -6.1203
Max Act: 5.9015. Min Act: -0.1700
Data Index: 5861320 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1203. Min Range: -6.1203
Max Act: 5.8703. Min Act: -0.1700
Data Index: 8175314 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1203. Min Range: -6.1203
Max Act: 5.8078. Min Act: -0.1700
Data Index: 2768480 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1203. Min Range: -6.1203
Max Act: 5.8390. Min Act: -0.1700
Data Index: 1345222 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1203. Min Range: -6.1203
Max Act: 5.8078. Min Act: -0.1700
Data Index: 4627084 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1203. Min Range: -6.1203
Max Act: 5.8390. Min Act: -0.1700
Data Index: 6827588 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1203. Min Range: -6.1203
Max Act: 5.8390. Min Act: -0.1700
Data Index: 4781931 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1203. Min Range: -6.1203
Max Act: 5.8390. Min Act: -0.1700
Data Index: 3565351 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1203. Min Range: -6.1203
Max Act: 5.8078. Min Act: -0.1700
Data Index: 7340282 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1203. Min Range: -6.1203
Max Act: 5.8078. Min Act: -0.1700
Data Index: 6103491 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #19