Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5621 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7098. Min Range: -6.7098
Max Act: 6.7098. Min Act: -0.1700
Data Index: 3639975 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7098. Min Range: -6.7098
Max Act: 6.6786. Min Act: -0.1700
Data Index: 5757009 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7098. Min Range: -6.7098
Max Act: 6.6161. Min Act: -0.1700
Data Index: 224969 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7098. Min Range: -6.7098
Max Act: 6.5536. Min Act: -0.1700
Data Index: 1040321 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7098. Min Range: -6.7098
Max Act: 6.4911. Min Act: -0.1700
Data Index: 3252339 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7098. Min Range: -6.7098
Max Act: 6.3973. Min Act: -0.1700
Data Index: 1784942 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7098. Min Range: -6.7098
Max Act: 6.3348. Min Act: -0.1700
Data Index: 6822553 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7098. Min Range: -6.7098
Max Act: 6.3661. Min Act: -0.1700
Data Index: 1284882 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7098. Min Range: -6.7098
Max Act: 6.3348. Min Act: -0.1700
Data Index: 8111872 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7098. Min Range: -6.7098
Max Act: 6.3036. Min Act: -0.1700
Data Index: 6010501 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7098. Min Range: -6.7098
Max Act: 6.3348. Min Act: -0.1700
Data Index: 5248511 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7098. Min Range: -6.7098
Max Act: 6.3036. Min Act: -0.1700
Data Index: 472469 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7098. Min Range: -6.7098
Max Act: 6.3036. Min Act: -0.1700
Data Index: 6795560 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7098. Min Range: -6.7098
Max Act: 6.2723. Min Act: -0.1700
Data Index: 7527264 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7098. Min Range: -6.7098
Max Act: 6.2723. Min Act: -0.1700
Data Index: 3255705 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7098. Min Range: -6.7098
Max Act: 6.2723. Min Act: -0.1700
Data Index: 6616973 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7098. Min Range: -6.7098
Max Act: 6.2411. Min Act: -0.1700
Data Index: 5729062 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7098. Min Range: -6.7098
Max Act: 6.2098. Min Act: -0.1700
Data Index: 7213853 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7098. Min Range: -6.7098
Max Act: 6.2411. Min Act: -0.1700
Data Index: 4393677 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7098. Min Range: -6.7098
Max Act: 6.2098. Min Act: -0.1700
Data Index: 4357330 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #19