Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3325 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5256. Min Range: -6.5256
Max Act: 6.5256. Min Act: -0.1700
Data Index: 362632 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5256. Min Range: -6.5256
Max Act: 6.4318. Min Act: -0.1700
Data Index: 905446 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5256. Min Range: -6.5256
Max Act: 6.3693. Min Act: -0.1700
Data Index: 1216769 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5256. Min Range: -6.5256
Max Act: 6.3068. Min Act: -0.1700
Data Index: 758099 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5256. Min Range: -6.5256
Max Act: 6.2756. Min Act: -0.1700
Data Index: 7652611 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5256. Min Range: -6.5256
Max Act: 6.2756. Min Act: -0.1700
Data Index: 7749419 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5256. Min Range: -6.5256
Max Act: 6.2443. Min Act: -0.1700
Data Index: 2469893 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5256. Min Range: -6.5256
Max Act: 6.2443. Min Act: -0.1700
Data Index: 1444351 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5256. Min Range: -6.5256
Max Act: 6.2443. Min Act: -0.1700
Data Index: 6984128 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5256. Min Range: -6.5256
Max Act: 6.2131. Min Act: -0.1700
Data Index: 3387561 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5256. Min Range: -6.5256
Max Act: 6.2131. Min Act: -0.1700
Data Index: 4246945 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5256. Min Range: -6.5256
Max Act: 6.2131. Min Act: -0.1700
Data Index: 727266 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5256. Min Range: -6.5256
Max Act: 6.1506. Min Act: -0.1700
Data Index: 5461592 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5256. Min Range: -6.5256
Max Act: 6.2131. Min Act: -0.1700
Data Index: 4929607 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5256. Min Range: -6.5256
Max Act: 6.1506. Min Act: -0.1700
Data Index: 1049671 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5256. Min Range: -6.5256
Max Act: 6.1506. Min Act: -0.1700
Data Index: 8112457 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5256. Min Range: -6.5256
Max Act: 6.1193. Min Act: -0.1700
Data Index: 7983561 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5256. Min Range: -6.5256
Max Act: 6.1193. Min Act: -0.1700
Data Index: 191802 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5256. Min Range: -6.5256
Max Act: 6.1193. Min Act: -0.1700
Data Index: 1794514 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5256. Min Range: -6.5256
Max Act: 6.1193. Min Act: -0.1700
Data Index: 7499905 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19