Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2608 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.8032. Min Act: -0.1700
Data Index: 5910351 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.7720. Min Act: -0.1700
Data Index: 1785803 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.7720. Min Act: -0.1700
Data Index: 6100223 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.7720. Min Act: -0.1700
Data Index: 3631730 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.7407. Min Act: -0.1700
Data Index: 2944039 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.7407. Min Act: -0.1700
Data Index: 1137795 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.7095. Min Act: -0.1700
Data Index: 5539107 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.7095. Min Act: -0.1700
Data Index: 429948 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.7407. Min Act: -0.1700
Data Index: 6647650 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.7095. Min Act: -0.1700
Data Index: 2195518 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.7407. Min Act: -0.1700
Data Index: 1092538 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.6782. Min Act: -0.1700
Data Index: 4359329 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.6782. Min Act: -0.1700
Data Index: 4719252 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.6470. Min Act: -0.1700
Data Index: 2646970 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.6782. Min Act: -0.1700
Data Index: 6185386 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.7095. Min Act: -0.1700
Data Index: 578497 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.6782. Min Act: -0.1700
Data Index: 2999092 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.6782. Min Act: -0.1700
Data Index: 3667845 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.6157. Min Act: -0.1700
Data Index: 5152297 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.6470. Min Act: -0.1700
Data Index: 3500988 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #19