Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3585 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8933. Min Range: -7.8933
Max Act: 7.8933. Min Act: -0.1700
Data Index: 608227 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8933. Min Range: -7.8933
Max Act: 7.7995. Min Act: -0.1700
Data Index: 3135909 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8933. Min Range: -7.8933
Max Act: 7.6120. Min Act: -0.1700
Data Index: 257516 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8933. Min Range: -7.8933
Max Act: 7.5808. Min Act: -0.1700
Data Index: 4490610 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8933. Min Range: -7.8933
Max Act: 7.5183. Min Act: -0.1700
Data Index: 1187422 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8933. Min Range: -7.8933
Max Act: 7.5183. Min Act: -0.1700
Data Index: 6805459 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8933. Min Range: -7.8933
Max Act: 7.4558. Min Act: -0.1700
Data Index: 8379860 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8933. Min Range: -7.8933
Max Act: 7.4245. Min Act: -0.1700
Data Index: 3645938 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8933. Min Range: -7.8933
Max Act: 7.4558. Min Act: -0.1700
Data Index: 3750037 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8933. Min Range: -7.8933
Max Act: 7.4558. Min Act: -0.1700
Data Index: 1187430 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8933. Min Range: -7.8933
Max Act: 7.3933. Min Act: -0.1700
Data Index: 6495193 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8933. Min Range: -7.8933
Max Act: 7.4245. Min Act: -0.1700
Data Index: 6233150 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8933. Min Range: -7.8933
Max Act: 7.3933. Min Act: -0.1700
Data Index: 5336715 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8933. Min Range: -7.8933
Max Act: 7.3933. Min Act: -0.1700
Data Index: 356681 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8933. Min Range: -7.8933
Max Act: 7.3933. Min Act: -0.1700
Data Index: 2374292 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8933. Min Range: -7.8933
Max Act: 7.3308. Min Act: -0.1700
Data Index: 4653658 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8933. Min Range: -7.8933
Max Act: 7.3308. Min Act: -0.1700
Data Index: 3873875 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8933. Min Range: -7.8933
Max Act: 7.3620. Min Act: -0.1700
Data Index: 6805463 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8933. Min Range: -7.8933
Max Act: 7.3620. Min Act: -0.1700
Data Index: 5336709 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8933. Min Range: -7.8933
Max Act: 7.3308. Min Act: -0.1700
Data Index: 1195591 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #19