Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 537 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6025. Min Range: -3.6025
Max Act: 3.6025. Min Act: -0.1700
Data Index: 4543160 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6025. Min Range: -3.6025
Max Act: 3.5399. Min Act: -0.1700
Data Index: 6916185 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6025. Min Range: -3.6025
Max Act: 3.5712. Min Act: -0.1700
Data Index: 1159176 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6025. Min Range: -3.6025
Max Act: 3.5399. Min Act: -0.1700
Data Index: 7187839 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6025. Min Range: -3.6025
Max Act: 3.5712. Min Act: -0.1700
Data Index: 864986 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6025. Min Range: -3.6025
Max Act: 3.5712. Min Act: -0.1700
Data Index: 6394203 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6025. Min Range: -3.6025
Max Act: 3.5085. Min Act: -0.1700
Data Index: 3323575 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6025. Min Range: -3.6025
Max Act: 3.4772. Min Act: -0.1700
Data Index: 2244317 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6025. Min Range: -3.6025
Max Act: 3.4772. Min Act: -0.1700
Data Index: 6867715 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6025. Min Range: -3.6025
Max Act: 3.4772. Min Act: -0.1700
Data Index: 6733193 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6025. Min Range: -3.6025
Max Act: 3.4772. Min Act: -0.1700
Data Index: 7625269 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6025. Min Range: -3.6025
Max Act: 3.4772. Min Act: -0.1700
Data Index: 7479148 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6025. Min Range: -3.6025
Max Act: 3.4772. Min Act: -0.1700
Data Index: 5881121 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6025. Min Range: -3.6025
Max Act: 3.4772. Min Act: -0.1700
Data Index: 4019650 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6025. Min Range: -3.6025
Max Act: 3.4772. Min Act: -0.1700
Data Index: 8593407 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6025. Min Range: -3.6025
Max Act: 3.4459. Min Act: -0.1700
Data Index: 4780772 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6025. Min Range: -3.6025
Max Act: 3.4459. Min Act: -0.1700
Data Index: 755986 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6025. Min Range: -3.6025
Max Act: 3.4459. Min Act: -0.1700
Data Index: 7343638 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6025. Min Range: -3.6025
Max Act: 3.4459. Min Act: -0.1700
Data Index: 4206493 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6025. Min Range: -3.6025
Max Act: 3.4459. Min Act: -0.1700
Data Index: 7643133 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19