Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1825 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9679. Min Range: -3.9679
Max Act: 3.9679. Min Act: -0.1700
Data Index: 2352055 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9679. Min Range: -3.9679
Max Act: 3.9367. Min Act: -0.1700
Data Index: 4691049 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9679. Min Range: -3.9679
Max Act: 3.9367. Min Act: -0.1700
Data Index: 7807736 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9679. Min Range: -3.9679
Max Act: 3.9054. Min Act: -0.1700
Data Index: 6171357 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9679. Min Range: -3.9679
Max Act: 3.8741. Min Act: -0.1700
Data Index: 8709256 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9679. Min Range: -3.9679
Max Act: 3.8741. Min Act: -0.1700
Data Index: 4651717 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9679. Min Range: -3.9679
Max Act: 3.8741. Min Act: -0.1700
Data Index: 6975279 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9679. Min Range: -3.9679
Max Act: 3.8429. Min Act: -0.1700
Data Index: 8455849 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9679. Min Range: -3.9679
Max Act: 3.8429. Min Act: -0.1700
Data Index: 5273276 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9679. Min Range: -3.9679
Max Act: 3.8116. Min Act: -0.1700
Data Index: 4518448 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9679. Min Range: -3.9679
Max Act: 3.8116. Min Act: -0.1700
Data Index: 1100955 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9679. Min Range: -3.9679
Max Act: 3.8116. Min Act: -0.1700
Data Index: 1613265 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9679. Min Range: -3.9679
Max Act: 3.8116. Min Act: -0.1700
Data Index: 2429491 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9679. Min Range: -3.9679
Max Act: 3.8116. Min Act: -0.1700
Data Index: 4953522 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9679. Min Range: -3.9679
Max Act: 3.8116. Min Act: -0.1700
Data Index: 5132456 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9679. Min Range: -3.9679
Max Act: 3.7803. Min Act: -0.1700
Data Index: 3163904 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9679. Min Range: -3.9679
Max Act: 3.7803. Min Act: -0.1700
Data Index: 4695837 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9679. Min Range: -3.9679
Max Act: 3.7803. Min Act: -0.1700
Data Index: 2472392 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9679. Min Range: -3.9679
Max Act: 3.7803. Min Act: -0.1700
Data Index: 4784609 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9679. Min Range: -3.9679
Max Act: 3.7803. Min Act: -0.1700
Data Index: 2776591 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19