Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 12 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0962. Min Range: -6.0962
Max Act: 6.0962. Min Act: -0.1700
Data Index: 731437 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0962. Min Range: -6.0962
Max Act: 6.0024. Min Act: -0.1700
Data Index: 5321930 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0962. Min Range: -6.0962
Max Act: 5.8462. Min Act: -0.1700
Data Index: 4149155 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0962. Min Range: -6.0962
Max Act: 5.7837. Min Act: -0.1700
Data Index: 3897678 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0962. Min Range: -6.0962
Max Act: 5.7212. Min Act: -0.1700
Data Index: 1202341 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0962. Min Range: -6.0962
Max Act: 5.7212. Min Act: -0.1700
Data Index: 2199165 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0962. Min Range: -6.0962
Max Act: 5.6899. Min Act: -0.1700
Data Index: 7828481 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0962. Min Range: -6.0962
Max Act: 5.6899. Min Act: -0.1700
Data Index: 3614909 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0962. Min Range: -6.0962
Max Act: 5.6587. Min Act: -0.1700
Data Index: 4582533 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0962. Min Range: -6.0962
Max Act: 5.6587. Min Act: -0.1700
Data Index: 426350 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0962. Min Range: -6.0962
Max Act: 5.6274. Min Act: -0.1700
Data Index: 1450908 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0962. Min Range: -6.0962
Max Act: 5.6587. Min Act: -0.1700
Data Index: 5807984 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0962. Min Range: -6.0962
Max Act: 5.6274. Min Act: -0.1700
Data Index: 498984 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0962. Min Range: -6.0962
Max Act: 5.6274. Min Act: -0.1700
Data Index: 998046 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0962. Min Range: -6.0962
Max Act: 5.6274. Min Act: -0.1698
Data Index: 8591288 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0962. Min Range: -6.0962
Max Act: 5.6274. Min Act: -0.1700
Data Index: 2737914 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0962. Min Range: -6.0962
Max Act: 5.5962. Min Act: -0.1700
Data Index: 3786586 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0962. Min Range: -6.0962
Max Act: 5.5962. Min Act: -0.1700
Data Index: 4933717 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0962. Min Range: -6.0962
Max Act: 5.5962. Min Act: -0.1700
Data Index: 3730386 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0962. Min Range: -6.0962
Max Act: 5.5962. Min Act: -0.1700
Data Index: 6033830 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #19