Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 319 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6911. Min Range: -2.6911
Max Act: 2.6911. Min Act: -0.1700
Data Index: 5362013 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6911. Min Range: -2.6911
Max Act: 2.6751. Min Act: -0.1700
Data Index: 1379694 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6911. Min Range: -2.6911
Max Act: 2.6911. Min Act: -0.1700
Data Index: 4161164 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6911. Min Range: -2.6911
Max Act: 2.6751. Min Act: -0.1700
Data Index: 4934271 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6911. Min Range: -2.6911
Max Act: 2.6591. Min Act: -0.1700
Data Index: 5825767 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6911. Min Range: -2.6911
Max Act: 2.6591. Min Act: -0.1700
Data Index: 6706099 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6911. Min Range: -2.6911
Max Act: 2.6591. Min Act: -0.1700
Data Index: 2356539 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6911. Min Range: -2.6911
Max Act: 2.6591. Min Act: -0.1700
Data Index: 5820056 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6911. Min Range: -2.6911
Max Act: 2.6430. Min Act: -0.1700
Data Index: 3695172 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6911. Min Range: -2.6911
Max Act: 2.6430. Min Act: -0.1700
Data Index: 6092760 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6911. Min Range: -2.6911
Max Act: 2.6430. Min Act: -0.1700
Data Index: 880322 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6911. Min Range: -2.6911
Max Act: 2.6430. Min Act: -0.1700
Data Index: 6131078 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6911. Min Range: -2.6911
Max Act: 2.6430. Min Act: -0.1700
Data Index: 1939403 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6911. Min Range: -2.6911
Max Act: 2.6270. Min Act: -0.1700
Data Index: 6726035 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6911. Min Range: -2.6911
Max Act: 2.6270. Min Act: -0.1700
Data Index: 944 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6911. Min Range: -2.6911
Max Act: 2.6270. Min Act: -0.1700
Data Index: 5506244 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6911. Min Range: -2.6911
Max Act: 2.6270. Min Act: -0.1700
Data Index: 5173659 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6911. Min Range: -2.6911
Max Act: 2.6270. Min Act: -0.1700
Data Index: 972951 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6911. Min Range: -2.6911
Max Act: 2.6270. Min Act: -0.1700
Data Index: 2453933 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6911. Min Range: -2.6911
Max Act: 2.6270. Min Act: -0.1700
Data Index: 105419 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19