Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 809 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8938. Min Range: -3.8938
Max Act: 3.8938. Min Act: -0.1700
Data Index: 2198487 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8938. Min Range: -3.8938
Max Act: 3.8938. Min Act: -0.1700
Data Index: 4257079 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8938. Min Range: -3.8938
Max Act: 3.8938. Min Act: -0.1700
Data Index: 5021858 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8938. Min Range: -3.8938
Max Act: 3.8938. Min Act: -0.1700
Data Index: 5596607 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8938. Min Range: -3.8938
Max Act: 3.8312. Min Act: -0.1700
Data Index: 7417886 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8938. Min Range: -3.8938
Max Act: 3.8312. Min Act: -0.1700
Data Index: 7880685 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8938. Min Range: -3.8938
Max Act: 3.7999. Min Act: -0.1700
Data Index: 608632 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8938. Min Range: -3.8938
Max Act: 3.7999. Min Act: -0.1700
Data Index: 589531 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8938. Min Range: -3.8938
Max Act: 3.7999. Min Act: -0.1700
Data Index: 5743 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8938. Min Range: -3.8938
Max Act: 3.7999. Min Act: -0.1700
Data Index: 554609 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8938. Min Range: -3.8938
Max Act: 3.7999. Min Act: -0.1700
Data Index: 498213 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8938. Min Range: -3.8938
Max Act: 3.7999. Min Act: -0.1700
Data Index: 496527 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8938. Min Range: -3.8938
Max Act: 3.7999. Min Act: -0.1700
Data Index: 470306 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8938. Min Range: -3.8938
Max Act: 3.7999. Min Act: -0.1700
Data Index: 429938 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8938. Min Range: -3.8938
Max Act: 3.7999. Min Act: -0.1700
Data Index: 362172 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8938. Min Range: -3.8938
Max Act: 3.7999. Min Act: -0.1700
Data Index: 45734 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8938. Min Range: -3.8938
Max Act: 3.7999. Min Act: -0.1700
Data Index: 349234 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8938. Min Range: -3.8938
Max Act: 3.7999. Min Act: -0.1700
Data Index: 346854 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8938. Min Range: -3.8938
Max Act: 3.7999. Min Act: -0.1700
Data Index: 301601 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8938. Min Range: -3.8938
Max Act: 3.7999. Min Act: -0.1700
Data Index: 288676 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19