Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5334 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9601. Min Range: -6.9601
Max Act: 6.9601. Min Act: -0.1700
Data Index: 4470427 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9601. Min Range: -6.9601
Max Act: 6.8351. Min Act: -0.1700
Data Index: 7543313 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9601. Min Range: -6.9601
Max Act: 6.6163. Min Act: -0.1700
Data Index: 8786439 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9601. Min Range: -6.9601
Max Act: 6.5226. Min Act: -0.1700
Data Index: 3073451 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9601. Min Range: -6.9601
Max Act: 6.5226. Min Act: -0.1700
Data Index: 7064206 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9601. Min Range: -6.9601
Max Act: 6.5226. Min Act: -0.1700
Data Index: 7908368 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9601. Min Range: -6.9601
Max Act: 6.4913. Min Act: -0.1700
Data Index: 8824649 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9601. Min Range: -6.9601
Max Act: 6.3976. Min Act: -0.1700
Data Index: 3256323 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9601. Min Range: -6.9601
Max Act: 6.3663. Min Act: -0.1700
Data Index: 697754 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9601. Min Range: -6.9601
Max Act: 6.3351. Min Act: -0.1700
Data Index: 5849831 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9601. Min Range: -6.9601
Max Act: 6.3351. Min Act: -0.1700
Data Index: 5486656 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9601. Min Range: -6.9601
Max Act: 6.3351. Min Act: -0.1700
Data Index: 4983741 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9601. Min Range: -6.9601
Max Act: 6.2413. Min Act: -0.1700
Data Index: 3559973 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9601. Min Range: -6.9601
Max Act: 6.2101. Min Act: -0.1700
Data Index: 6313647 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9601. Min Range: -6.9601
Max Act: 6.0851. Min Act: -0.1700
Data Index: 6697846 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9601. Min Range: -6.9601
Max Act: 6.1163. Min Act: -0.1700
Data Index: 3039189 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9601. Min Range: -6.9601
Max Act: 6.1163. Min Act: -0.1700
Data Index: 3288037 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9601. Min Range: -6.9601
Max Act: 6.1163. Min Act: -0.1700
Data Index: 7908364 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9601. Min Range: -6.9601
Max Act: 6.1163. Min Act: -0.1700
Data Index: 7096245 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9601. Min Range: -6.9601
Max Act: 6.1163. Min Act: -0.1700
Data Index: 2840101 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #19