Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4577 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5978. Min Range: -3.5978
Max Act: 3.5978. Min Act: -0.1700
Data Index: 7509392 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5978. Min Range: -3.5978
Max Act: 3.5978. Min Act: -0.1700
Data Index: 3837690 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5978. Min Range: -3.5978
Max Act: 3.5664. Min Act: -0.1700
Data Index: 371403 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5978. Min Range: -3.5978
Max Act: 3.5664. Min Act: -0.1700
Data Index: 8465162 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5978. Min Range: -3.5978
Max Act: 3.5664. Min Act: -0.1700
Data Index: 6823084 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5978. Min Range: -3.5978
Max Act: 3.5664. Min Act: -0.1700
Data Index: 3185642 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5978. Min Range: -3.5978
Max Act: 3.5664. Min Act: -0.1700
Data Index: 6259201 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5978. Min Range: -3.5978
Max Act: 3.5664. Min Act: -0.1700
Data Index: 5738897 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5978. Min Range: -3.5978
Max Act: 3.5664. Min Act: -0.1700
Data Index: 5720974 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5978. Min Range: -3.5978
Max Act: 3.5351. Min Act: -0.1700
Data Index: 2997512 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5978. Min Range: -3.5978
Max Act: 3.5351. Min Act: -0.1700
Data Index: 2930467 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5978. Min Range: -3.5978
Max Act: 3.5351. Min Act: -0.1700
Data Index: 3879582 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5978. Min Range: -3.5978
Max Act: 3.5351. Min Act: -0.1700
Data Index: 3862858 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5978. Min Range: -3.5978
Max Act: 3.5351. Min Act: -0.1700
Data Index: 852756 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5978. Min Range: -3.5978
Max Act: 3.5351. Min Act: -0.1700
Data Index: 1281522 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5978. Min Range: -3.5978
Max Act: 3.5038. Min Act: -0.1700
Data Index: 2650923 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5978. Min Range: -3.5978
Max Act: 3.5038. Min Act: -0.1700
Data Index: 3738045 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5978. Min Range: -3.5978
Max Act: 3.4725. Min Act: -0.1700
Data Index: 1172213 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5978. Min Range: -3.5978
Max Act: 3.5038. Min Act: -0.1700
Data Index: 1619406 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5978. Min Range: -3.5978
Max Act: 3.5038. Min Act: -0.1700
Data Index: 1435592 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19