Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4661 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.3938. Min Range: -8.3938
Max Act: 8.3938. Min Act: -0.1700
Data Index: 4098306 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3938. Min Range: -8.3938
Max Act: 8.3313. Min Act: -0.1700
Data Index: 5768374 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3938. Min Range: -8.3938
Max Act: 8.3313. Min Act: -0.1700
Data Index: 3838011 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3938. Min Range: -8.3938
Max Act: 8.2688. Min Act: -0.1700
Data Index: 1049258 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3938. Min Range: -8.3938
Max Act: 8.2376. Min Act: -0.1700
Data Index: 6157269 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3938. Min Range: -8.3938
Max Act: 8.2376. Min Act: -0.1700
Data Index: 4105768 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3938. Min Range: -8.3938
Max Act: 8.1751. Min Act: -0.1700
Data Index: 8159241 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3938. Min Range: -8.3938
Max Act: 8.1438. Min Act: -0.1700
Data Index: 5426571 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3938. Min Range: -8.3938
Max Act: 8.1438. Min Act: -0.1700
Data Index: 8061499 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3938. Min Range: -8.3938
Max Act: 8.1438. Min Act: -0.1700
Data Index: 4884339 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3938. Min Range: -8.3938
Max Act: 8.1126. Min Act: -0.1700
Data Index: 6676485 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3938. Min Range: -8.3938
Max Act: 8.1126. Min Act: -0.1700
Data Index: 697420 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3938. Min Range: -8.3938
Max Act: 8.1438. Min Act: -0.1700
Data Index: 4364263 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3938. Min Range: -8.3938
Max Act: 8.1126. Min Act: -0.1700
Data Index: 5808613 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3938. Min Range: -8.3938
Max Act: 8.0813. Min Act: -0.1700
Data Index: 3949737 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3938. Min Range: -8.3938
Max Act: 8.0501. Min Act: -0.1700
Data Index: 2893927 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3938. Min Range: -8.3938
Max Act: 8.0501. Min Act: -0.1700
Data Index: 766438 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3938. Min Range: -8.3938
Max Act: 8.0813. Min Act: -0.1700
Data Index: 7403581 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3938. Min Range: -8.3938
Max Act: 8.0188. Min Act: -0.1700
Data Index: 5429943 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3938. Min Range: -8.3938
Max Act: 8.0501. Min Act: -0.1700
Data Index: 1960611 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #19