Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2697 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6139. Min Range: -3.6139
Max Act: 3.6139. Min Act: -0.1700
Data Index: 5964999 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6139. Min Range: -3.6139
Max Act: 3.5826. Min Act: -0.1700
Data Index: 5975727 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6139. Min Range: -3.6139
Max Act: 3.5826. Min Act: -0.1700
Data Index: 5661317 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6139. Min Range: -3.6139
Max Act: 3.5826. Min Act: -0.1700
Data Index: 8409670 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6139. Min Range: -3.6139
Max Act: 3.5826. Min Act: -0.1700
Data Index: 5802889 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6139. Min Range: -3.6139
Max Act: 3.5513. Min Act: -0.1700
Data Index: 3544119 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6139. Min Range: -3.6139
Max Act: 3.5513. Min Act: -0.1700
Data Index: 6044034 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6139. Min Range: -3.6139
Max Act: 3.5513. Min Act: -0.1700
Data Index: 6961850 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6139. Min Range: -3.6139
Max Act: 3.5513. Min Act: -0.1700
Data Index: 5302714 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6139. Min Range: -3.6139
Max Act: 3.5513. Min Act: -0.1700
Data Index: 864037 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6139. Min Range: -3.6139
Max Act: 3.5513. Min Act: -0.1700
Data Index: 4118581 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6139. Min Range: -3.6139
Max Act: 3.4887. Min Act: -0.1700
Data Index: 897391 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6139. Min Range: -3.6139
Max Act: 3.4887. Min Act: -0.1700
Data Index: 7479287 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6139. Min Range: -3.6139
Max Act: 3.4887. Min Act: -0.1700
Data Index: 7046554 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6139. Min Range: -3.6139
Max Act: 3.4573. Min Act: -0.1700
Data Index: 7624229 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6139. Min Range: -3.6139
Max Act: 3.4887. Min Act: -0.1700
Data Index: 7100436 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6139. Min Range: -3.6139
Max Act: 3.4260. Min Act: -0.1700
Data Index: 3877741 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6139. Min Range: -3.6139
Max Act: 3.4260. Min Act: -0.1700
Data Index: 4708839 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6139. Min Range: -3.6139
Max Act: 3.4260. Min Act: -0.1699
Data Index: 4757194 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6139. Min Range: -3.6139
Max Act: 3.4260. Min Act: -0.1700
Data Index: 3354090 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19