Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5116 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1521. Min Range: -4.1521
Max Act: 4.1521. Min Act: -0.1700
Data Index: 343315 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1521. Min Range: -4.1521
Max Act: 4.0583. Min Act: -0.1700
Data Index: 1167569 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1521. Min Range: -4.1521
Max Act: 3.9958. Min Act: -0.1700
Data Index: 5613174 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1521. Min Range: -4.1521
Max Act: 3.9646. Min Act: -0.1700
Data Index: 6001232 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1521. Min Range: -4.1521
Max Act: 3.9646. Min Act: -0.1700
Data Index: 2076235 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1521. Min Range: -4.1521
Max Act: 3.9958. Min Act: -0.1700
Data Index: 1723133 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1521. Min Range: -4.1521
Max Act: 3.9646. Min Act: -0.1700
Data Index: 7661678 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1521. Min Range: -4.1521
Max Act: 3.9646. Min Act: -0.1700
Data Index: 7636415 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1521. Min Range: -4.1521
Max Act: 3.9646. Min Act: -0.1700
Data Index: 3680419 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1521. Min Range: -4.1521
Max Act: 3.9020. Min Act: -0.1700
Data Index: 968725 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1521. Min Range: -4.1521
Max Act: 3.9020. Min Act: -0.1700
Data Index: 3937011 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1521. Min Range: -4.1521
Max Act: 3.9333. Min Act: -0.1700
Data Index: 4595387 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1521. Min Range: -4.1521
Max Act: 3.9333. Min Act: -0.1700
Data Index: 5610626 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1521. Min Range: -4.1521
Max Act: 3.9020. Min Act: -0.1700
Data Index: 6434127 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1521. Min Range: -4.1521
Max Act: 3.9333. Min Act: -0.1700
Data Index: 852830 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1521. Min Range: -4.1521
Max Act: 3.9333. Min Act: -0.1700
Data Index: 16635 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1521. Min Range: -4.1521
Max Act: 3.9333. Min Act: -0.1700
Data Index: 2781845 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1521. Min Range: -4.1521
Max Act: 3.9020. Min Act: -0.1700
Data Index: 2340145 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1521. Min Range: -4.1521
Max Act: 3.9020. Min Act: -0.1700
Data Index: 4944943 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1521. Min Range: -4.1521
Max Act: 3.9020. Min Act: -0.1700
Data Index: 904423 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19