Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 591 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9082. Min Range: -5.9082
Max Act: 5.9082. Min Act: -0.1700
Data Index: 6820979 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9082. Min Range: -5.9082
Max Act: 5.8145. Min Act: -0.1700
Data Index: 7504678 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9082. Min Range: -5.9082
Max Act: 5.7520. Min Act: -0.1700
Data Index: 4514378 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9082. Min Range: -5.9082
Max Act: 5.7207. Min Act: -0.1700
Data Index: 3280513 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9082. Min Range: -5.9082
Max Act: 5.5957. Min Act: -0.1700
Data Index: 6574468 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9082. Min Range: -5.9082
Max Act: 5.5332. Min Act: -0.1700
Data Index: 5543200 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9082. Min Range: -5.9082
Max Act: 5.5645. Min Act: -0.1700
Data Index: 3366122 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9082. Min Range: -5.9082
Max Act: 5.5020. Min Act: -0.1700
Data Index: 3793658 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9082. Min Range: -5.9082
Max Act: 5.5020. Min Act: -0.1700
Data Index: 2820461 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9082. Min Range: -5.9082
Max Act: 5.4707. Min Act: -0.1700
Data Index: 5415743 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9082. Min Range: -5.9082
Max Act: 5.4707. Min Act: -0.1700
Data Index: 5232240 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9082. Min Range: -5.9082
Max Act: 5.4707. Min Act: -0.1700
Data Index: 5725047 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9082. Min Range: -5.9082
Max Act: 5.4082. Min Act: -0.1700
Data Index: 2875934 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9082. Min Range: -5.9082
Max Act: 5.4395. Min Act: -0.1700
Data Index: 6974316 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9082. Min Range: -5.9082
Max Act: 5.3770. Min Act: -0.1700
Data Index: 1397013 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9082. Min Range: -5.9082
Max Act: 5.3457. Min Act: -0.1700
Data Index: 197847 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9082. Min Range: -5.9082
Max Act: 5.3457. Min Act: -0.1700
Data Index: 4022511 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9082. Min Range: -5.9082
Max Act: 5.3770. Min Act: -0.1700
Data Index: 1696885 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9082. Min Range: -5.9082
Max Act: 5.3770. Min Act: -0.1700
Data Index: 6383863 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9082. Min Range: -5.9082
Max Act: 5.3457. Min Act: -0.1700
Data Index: 5596474 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #19