Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2532 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.6953. Min Range: -8.6953
Max Act: 8.6953. Min Act: -0.1700
Data Index: 6270701 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6953. Min Range: -8.6953
Max Act: 8.6953. Min Act: -0.1700
Data Index: 6246191 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6953. Min Range: -8.6953
Max Act: 8.3828. Min Act: -0.1700
Data Index: 4247001 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6953. Min Range: -8.6953
Max Act: 8.2578. Min Act: -0.1700
Data Index: 5112341 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6953. Min Range: -8.6953
Max Act: 8.1328. Min Act: -0.1700
Data Index: 3749106 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6953. Min Range: -8.6953
Max Act: 8.1328. Min Act: -0.1700
Data Index: 7635764 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6953. Min Range: -8.6953
Max Act: 8.0703. Min Act: -0.1700
Data Index: 7707371 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6953. Min Range: -8.6953
Max Act: 8.0703. Min Act: -0.1700
Data Index: 5381965 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6953. Min Range: -8.6953
Max Act: 8.0703. Min Act: -0.1700
Data Index: 5353475 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6953. Min Range: -8.6953
Max Act: 8.0703. Min Act: -0.1700
Data Index: 6800231 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6953. Min Range: -8.6953
Max Act: 8.0703. Min Act: -0.1700
Data Index: 7506789 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6953. Min Range: -8.6953
Max Act: 8.0078. Min Act: -0.1700
Data Index: 7620887 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6953. Min Range: -8.6953
Max Act: 7.9453. Min Act: -0.1700
Data Index: 5599613 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6953. Min Range: -8.6953
Max Act: 8.0078. Min Act: -0.1700
Data Index: 7976073 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6953. Min Range: -8.6953
Max Act: 8.0078. Min Act: -0.1700
Data Index: 6938111 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6953. Min Range: -8.6953
Max Act: 8.0078. Min Act: -0.1700
Data Index: 4798782 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6953. Min Range: -8.6953
Max Act: 8.0078. Min Act: -0.1700
Data Index: 7930684 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6953. Min Range: -8.6953
Max Act: 7.9453. Min Act: -0.1700
Data Index: 2859692 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6953. Min Range: -8.6953
Max Act: 7.9453. Min Act: -0.1700
Data Index: 8728342 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6953. Min Range: -8.6953
Max Act: 7.9453. Min Act: -0.1700
Data Index: 1722477 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #19