Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2143 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9769. Min Range: -2.9769
Max Act: 2.9769. Min Act: -0.1700
Data Index: 7391578 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9769. Min Range: -2.9769
Max Act: 2.9769. Min Act: -0.1700
Data Index: 1222052 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9769. Min Range: -2.9769
Max Act: 2.9610. Min Act: -0.1700
Data Index: 7651179 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9769. Min Range: -2.9769
Max Act: 2.9452. Min Act: -0.1700
Data Index: 7035884 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9769. Min Range: -2.9769
Max Act: 2.9452. Min Act: -0.1700
Data Index: 1011845 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9769. Min Range: -2.9769
Max Act: 2.9452. Min Act: -0.1700
Data Index: 4890274 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9769. Min Range: -2.9769
Max Act: 2.9452. Min Act: -0.1700
Data Index: 6396930 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9769. Min Range: -2.9769
Max Act: 2.9452. Min Act: -0.1700
Data Index: 8412914 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9769. Min Range: -2.9769
Max Act: 2.9294. Min Act: -0.1700
Data Index: 4472800 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9769. Min Range: -2.9769
Max Act: 2.9294. Min Act: -0.1700
Data Index: 1947116 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9769. Min Range: -2.9769
Max Act: 2.9294. Min Act: -0.1700
Data Index: 5341463 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9769. Min Range: -2.9769
Max Act: 2.9294. Min Act: -0.1700
Data Index: 203854 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9769. Min Range: -2.9769
Max Act: 2.9135. Min Act: -0.1700
Data Index: 7128595 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9769. Min Range: -2.9769
Max Act: 2.9135. Min Act: -0.1700
Data Index: 3590161 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9769. Min Range: -2.9769
Max Act: 2.9135. Min Act: -0.1700
Data Index: 8288771 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9769. Min Range: -2.9769
Max Act: 2.9135. Min Act: -0.1700
Data Index: 2703358 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9769. Min Range: -2.9769
Max Act: 2.8977. Min Act: -0.1700
Data Index: 7686452 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9769. Min Range: -2.9769
Max Act: 2.9135. Min Act: -0.1700
Data Index: 2438541 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9769. Min Range: -2.9769
Max Act: 2.8977. Min Act: -0.1700
Data Index: 420037 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9769. Min Range: -2.9769
Max Act: 2.8977. Min Act: -0.1700
Data Index: 1011183 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #19