Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5182 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1090. Min Range: -3.1090
Max Act: 3.1090. Min Act: -0.1700
Data Index: 6479812 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1090. Min Range: -3.1090
Max Act: 3.0932. Min Act: -0.1700
Data Index: 476000 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1090. Min Range: -3.1090
Max Act: 3.0774. Min Act: -0.1700
Data Index: 4765671 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1090. Min Range: -3.1090
Max Act: 3.0774. Min Act: -0.1700
Data Index: 7413307 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1090. Min Range: -3.1090
Max Act: 3.0774. Min Act: -0.1700
Data Index: 5095918 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1090. Min Range: -3.1090
Max Act: 3.0617. Min Act: -0.1700
Data Index: 7553899 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1090. Min Range: -3.1090
Max Act: 3.0617. Min Act: -0.1700
Data Index: 8577804 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1090. Min Range: -3.1090
Max Act: 3.0459. Min Act: -0.1700
Data Index: 5529797 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1090. Min Range: -3.1090
Max Act: 3.0459. Min Act: -0.1700
Data Index: 490666 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1090. Min Range: -3.1090
Max Act: 3.0301. Min Act: -0.1700
Data Index: 126961 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1090. Min Range: -3.1090
Max Act: 3.0301. Min Act: -0.1700
Data Index: 514347 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1090. Min Range: -3.1090
Max Act: 3.0459. Min Act: -0.1700
Data Index: 3838926 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1090. Min Range: -3.1090
Max Act: 3.0301. Min Act: -0.1700
Data Index: 1228320 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1090. Min Range: -3.1090
Max Act: 3.0301. Min Act: -0.1700
Data Index: 7426089 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1090. Min Range: -3.1090
Max Act: 3.0301. Min Act: -0.1700
Data Index: 6622577 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1090. Min Range: -3.1090
Max Act: 3.0143. Min Act: -0.1700
Data Index: 4528869 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1090. Min Range: -3.1090
Max Act: 3.0301. Min Act: -0.1700
Data Index: 2645632 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1090. Min Range: -3.1090
Max Act: 3.0143. Min Act: -0.1700
Data Index: 4783111 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1090. Min Range: -3.1090
Max Act: 3.0143. Min Act: -0.1700
Data Index: 1405640 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1090. Min Range: -3.1090
Max Act: 3.0143. Min Act: -0.1700
Data Index: 3930485 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #19