Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4866 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9252. Min Range: -4.9252
Max Act: 4.9252. Min Act: -0.1700
Data Index: 1489008 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9252. Min Range: -4.9252
Max Act: 4.8314. Min Act: -0.1700
Data Index: 3031289 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9252. Min Range: -4.9252
Max Act: 4.7689. Min Act: -0.1700
Data Index: 6188625 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9252. Min Range: -4.9252
Max Act: 4.7377. Min Act: -0.1700
Data Index: 5704184 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9252. Min Range: -4.9252
Max Act: 4.7064. Min Act: -0.1700
Data Index: 4496803 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9252. Min Range: -4.9252
Max Act: 4.7064. Min Act: -0.1700
Data Index: 2884476 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9252. Min Range: -4.9252
Max Act: 4.7064. Min Act: -0.1700
Data Index: 4237566 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9252. Min Range: -4.9252
Max Act: 4.7064. Min Act: -0.1700
Data Index: 2055241 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9252. Min Range: -4.9252
Max Act: 4.6752. Min Act: -0.1700
Data Index: 3983031 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9252. Min Range: -4.9252
Max Act: 4.6752. Min Act: -0.1700
Data Index: 8464283 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9252. Min Range: -4.9252
Max Act: 4.6752. Min Act: -0.1700
Data Index: 6971537 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9252. Min Range: -4.9252
Max Act: 4.6752. Min Act: -0.1700
Data Index: 8696110 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9252. Min Range: -4.9252
Max Act: 4.6752. Min Act: -0.1700
Data Index: 1764433 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9252. Min Range: -4.9252
Max Act: 4.6439. Min Act: -0.1700
Data Index: 979797 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9252. Min Range: -4.9252
Max Act: 4.6439. Min Act: -0.1700
Data Index: 4502274 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9252. Min Range: -4.9252
Max Act: 4.6439. Min Act: -0.1700
Data Index: 5466137 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9252. Min Range: -4.9252
Max Act: 4.5814. Min Act: -0.1700
Data Index: 2071050 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9252. Min Range: -4.9252
Max Act: 4.6439. Min Act: -0.1700
Data Index: 972909 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9252. Min Range: -4.9252
Max Act: 4.6127. Min Act: -0.1700
Data Index: 4858656 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9252. Min Range: -4.9252
Max Act: 4.6127. Min Act: -0.1700
Data Index: 7646789 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #19