Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3564 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8895. Min Range: -3.8895
Max Act: 3.8895. Min Act: -0.1700
Data Index: 2709257 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8895. Min Range: -3.8895
Max Act: 3.8582. Min Act: -0.1700
Data Index: 7249723 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8895. Min Range: -3.8895
Max Act: 3.8269. Min Act: -0.1700
Data Index: 46535 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8895. Min Range: -3.8895
Max Act: 3.7957. Min Act: -0.1700
Data Index: 3534030 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8895. Min Range: -3.8895
Max Act: 3.8269. Min Act: -0.1700
Data Index: 1221440 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8895. Min Range: -3.8895
Max Act: 3.8269. Min Act: -0.1700
Data Index: 8219143 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8895. Min Range: -3.8895
Max Act: 3.7957. Min Act: -0.1700
Data Index: 7487421 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8895. Min Range: -3.8895
Max Act: 3.7957. Min Act: -0.1700
Data Index: 953224 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8895. Min Range: -3.8895
Max Act: 3.7644. Min Act: -0.1700
Data Index: 6717728 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8895. Min Range: -3.8895
Max Act: 3.7644. Min Act: -0.1700
Data Index: 8152202 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8895. Min Range: -3.8895
Max Act: 3.7644. Min Act: -0.1700
Data Index: 8182810 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8895. Min Range: -3.8895
Max Act: 3.7644. Min Act: -0.1700
Data Index: 236117 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8895. Min Range: -3.8895
Max Act: 3.7644. Min Act: -0.1700
Data Index: 4572294 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8895. Min Range: -3.8895
Max Act: 3.7644. Min Act: -0.1700
Data Index: 3509611 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8895. Min Range: -3.8895
Max Act: 3.7331. Min Act: -0.1700
Data Index: 7062462 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8895. Min Range: -3.8895
Max Act: 3.7331. Min Act: -0.1700
Data Index: 625304 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8895. Min Range: -3.8895
Max Act: 3.7331. Min Act: -0.1700
Data Index: 7573975 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8895. Min Range: -3.8895
Max Act: 3.7331. Min Act: -0.1700
Data Index: 4239426 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8895. Min Range: -3.8895
Max Act: 3.7331. Min Act: -0.1700
Data Index: 4783596 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8895. Min Range: -3.8895
Max Act: 3.7331. Min Act: -0.1700
Data Index: 5044569 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19