Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2636 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6038. Min Range: -3.6038
Max Act: 3.6038. Min Act: -0.1700
Data Index: 436547 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6038. Min Range: -3.6038
Max Act: 3.5725. Min Act: -0.1700
Data Index: 5384919 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6038. Min Range: -3.6038
Max Act: 3.5412. Min Act: -0.1700
Data Index: 7650128 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6038. Min Range: -3.6038
Max Act: 3.5412. Min Act: -0.1700
Data Index: 2121799 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6038. Min Range: -3.6038
Max Act: 3.5099. Min Act: -0.1700
Data Index: 8186495 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6038. Min Range: -3.6038
Max Act: 3.5099. Min Act: -0.1700
Data Index: 4604525 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6038. Min Range: -3.6038
Max Act: 3.5099. Min Act: -0.1700
Data Index: 2426542 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6038. Min Range: -3.6038
Max Act: 3.5099. Min Act: -0.1700
Data Index: 3630931 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6038. Min Range: -3.6038
Max Act: 3.5099. Min Act: -0.1700
Data Index: 8315110 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6038. Min Range: -3.6038
Max Act: 3.5099. Min Act: -0.1700
Data Index: 8196795 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6038. Min Range: -3.6038
Max Act: 3.4786. Min Act: -0.1700
Data Index: 3601303 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6038. Min Range: -3.6038
Max Act: 3.4786. Min Act: -0.1700
Data Index: 1691002 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6038. Min Range: -3.6038
Max Act: 3.4786. Min Act: -0.1700
Data Index: 888028 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6038. Min Range: -3.6038
Max Act: 3.4786. Min Act: -0.1700
Data Index: 4792868 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6038. Min Range: -3.6038
Max Act: 3.4786. Min Act: -0.1700
Data Index: 1839899 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6038. Min Range: -3.6038
Max Act: 3.4786. Min Act: -0.1700
Data Index: 5702185 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6038. Min Range: -3.6038
Max Act: 3.4629. Min Act: -0.1700
Data Index: 4182404 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6038. Min Range: -3.6038
Max Act: 3.4786. Min Act: -0.1700
Data Index: 4190812 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6038. Min Range: -3.6038
Max Act: 3.4786. Min Act: -0.1700
Data Index: 6910980 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6038. Min Range: -3.6038
Max Act: 3.4786. Min Act: -0.1700
Data Index: 393619 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19