Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2921 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8034. Min Range: -8.8034
Max Act: 8.8034. Min Act: -0.1700
Data Index: 7991634 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8034. Min Range: -8.8034
Max Act: 7.9909. Min Act: -0.1700
Data Index: 8096732 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8034. Min Range: -8.8034
Max Act: 7.8034. Min Act: -0.1700
Data Index: 2622450 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8034. Min Range: -8.8034
Max Act: 7.5534. Min Act: -0.1700
Data Index: 7682447 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8034. Min Range: -8.8034
Max Act: 7.4909. Min Act: -0.1700
Data Index: 6498813 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8034. Min Range: -8.8034
Max Act: 7.3659. Min Act: -0.1700
Data Index: 2326534 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8034. Min Range: -8.8034
Max Act: 7.3346. Min Act: -0.1700
Data Index: 4157930 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8034. Min Range: -8.8034
Max Act: 7.3034. Min Act: -0.1700
Data Index: 3607991 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8034. Min Range: -8.8034
Max Act: 7.3034. Min Act: -0.1700
Data Index: 1276552 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8034. Min Range: -8.8034
Max Act: 7.3346. Min Act: -0.1700
Data Index: 4936135 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8034. Min Range: -8.8034
Max Act: 7.2409. Min Act: -0.1700
Data Index: 8668835 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8034. Min Range: -8.8034
Max Act: 7.2409. Min Act: -0.1700
Data Index: 7038431 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8034. Min Range: -8.8034
Max Act: 7.2409. Min Act: -0.1700
Data Index: 8642105 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8034. Min Range: -8.8034
Max Act: 7.2096. Min Act: -0.1700
Data Index: 3349236 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8034. Min Range: -8.8034
Max Act: 7.1784. Min Act: -0.1700
Data Index: 2834606 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8034. Min Range: -8.8034
Max Act: 7.2096. Min Act: -0.1700
Data Index: 6256568 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8034. Min Range: -8.8034
Max Act: 7.1784. Min Act: -0.1700
Data Index: 4020604 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8034. Min Range: -8.8034
Max Act: 7.1784. Min Act: -0.1700
Data Index: 5122743 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8034. Min Range: -8.8034
Max Act: 7.1471. Min Act: -0.1700
Data Index: 6750934 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8034. Min Range: -8.8034
Max Act: 7.1159. Min Act: -0.1700
Data Index: 5661795 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #19