Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 13 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9057. Min Range: -4.9057
Max Act: 4.9057. Min Act: -0.1700
Data Index: 627251 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9057. Min Range: -4.9057
Max Act: 4.7807. Min Act: -0.1700
Data Index: 7701482 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9057. Min Range: -4.9057
Max Act: 4.7182. Min Act: -0.1700
Data Index: 6283411 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9057. Min Range: -4.9057
Max Act: 4.7182. Min Act: -0.1700
Data Index: 3460871 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9057. Min Range: -4.9057
Max Act: 4.7495. Min Act: -0.1700
Data Index: 6721196 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9057. Min Range: -4.9057
Max Act: 4.7182. Min Act: -0.1700
Data Index: 5153005 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9057. Min Range: -4.9057
Max Act: 4.6870. Min Act: -0.1700
Data Index: 3138140 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9057. Min Range: -4.9057
Max Act: 4.6870. Min Act: -0.1700
Data Index: 4270769 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9057. Min Range: -4.9057
Max Act: 4.6557. Min Act: -0.1700
Data Index: 8685174 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9057. Min Range: -4.9057
Max Act: 4.6557. Min Act: -0.1700
Data Index: 1091361 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9057. Min Range: -4.9057
Max Act: 4.6557. Min Act: -0.1700
Data Index: 4311537 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9057. Min Range: -4.9057
Max Act: 4.5620. Min Act: -0.1700
Data Index: 8365486 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9057. Min Range: -4.9057
Max Act: 4.5620. Min Act: -0.1700
Data Index: 2143458 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9057. Min Range: -4.9057
Max Act: 4.5620. Min Act: -0.1700
Data Index: 4618230 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9057. Min Range: -4.9057
Max Act: 4.5307. Min Act: -0.1700
Data Index: 2180298 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9057. Min Range: -4.9057
Max Act: 4.5307. Min Act: -0.1700
Data Index: 523507 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9057. Min Range: -4.9057
Max Act: 4.5307. Min Act: -0.1700
Data Index: 2017859 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9057. Min Range: -4.9057
Max Act: 4.5307. Min Act: -0.1700
Data Index: 3382604 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9057. Min Range: -4.9057
Max Act: 4.4995. Min Act: -0.1700
Data Index: 2468420 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9057. Min Range: -4.9057
Max Act: 4.4995. Min Act: -0.1700
Data Index: 7873067 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19