Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2916 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9013. Min Range: -5.9013
Max Act: 5.9013. Min Act: -0.1700
Data Index: 1378285 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9013. Min Range: -5.9013
Max Act: 5.8700. Min Act: -0.1700
Data Index: 2400760 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9013. Min Range: -5.9013
Max Act: 5.8700. Min Act: -0.1700
Data Index: 1613534 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9013. Min Range: -5.9013
Max Act: 5.8388. Min Act: -0.1700
Data Index: 4926123 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9013. Min Range: -5.9013
Max Act: 5.8388. Min Act: -0.1700
Data Index: 8555418 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9013. Min Range: -5.9013
Max Act: 5.7763. Min Act: -0.1700
Data Index: 7781989 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9013. Min Range: -5.9013
Max Act: 5.7450. Min Act: -0.1700
Data Index: 1218293 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9013. Min Range: -5.9013
Max Act: 5.7450. Min Act: -0.1700
Data Index: 3531008 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9013. Min Range: -5.9013
Max Act: 5.7138. Min Act: -0.1700
Data Index: 6824104 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9013. Min Range: -5.9013
Max Act: 5.6825. Min Act: -0.1700
Data Index: 7453925 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9013. Min Range: -5.9013
Max Act: 5.6825. Min Act: -0.1700
Data Index: 5184234 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9013. Min Range: -5.9013
Max Act: 5.6825. Min Act: -0.1700
Data Index: 555398 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9013. Min Range: -5.9013
Max Act: 5.6825. Min Act: -0.1700
Data Index: 1614243 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9013. Min Range: -5.9013
Max Act: 5.6513. Min Act: -0.1700
Data Index: 1546066 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9013. Min Range: -5.9013
Max Act: 5.6825. Min Act: -0.1700
Data Index: 5334615 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9013. Min Range: -5.9013
Max Act: 5.6825. Min Act: -0.1700
Data Index: 6046669 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9013. Min Range: -5.9013
Max Act: 5.6513. Min Act: -0.1700
Data Index: 5181015 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9013. Min Range: -5.9013
Max Act: 5.6513. Min Act: -0.1700
Data Index: 3429350 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9013. Min Range: -5.9013
Max Act: 5.6200. Min Act: -0.1700
Data Index: 1412566 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9013. Min Range: -5.9013
Max Act: 5.5888. Min Act: -0.1700
Data Index: 516003 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #19