Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3543 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2625. Min Range: -4.2625
Max Act: 4.2625. Min Act: -0.1700
Data Index: 2789633 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2625. Min Range: -4.2625
Max Act: 4.2000. Min Act: -0.1700
Data Index: 7927231 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2625. Min Range: -4.2625
Max Act: 4.1375. Min Act: -0.1700
Data Index: 2789634 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2625. Min Range: -4.2625
Max Act: 4.1062. Min Act: -0.1700
Data Index: 7031334 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2625. Min Range: -4.2625
Max Act: 4.0750. Min Act: -0.1700
Data Index: 2947305 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2625. Min Range: -4.2625
Max Act: 4.0437. Min Act: -0.1700
Data Index: 7043608 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2625. Min Range: -4.2625
Max Act: 4.0437. Min Act: -0.1700
Data Index: 7575399 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2625. Min Range: -4.2625
Max Act: 4.0750. Min Act: -0.1700
Data Index: 8132788 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2625. Min Range: -4.2625
Max Act: 4.0125. Min Act: -0.1700
Data Index: 3053747 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2625. Min Range: -4.2625
Max Act: 3.9812. Min Act: -0.1700
Data Index: 7024567 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2625. Min Range: -4.2625
Max Act: 3.9812. Min Act: -0.1700
Data Index: 1823469 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2625. Min Range: -4.2625
Max Act: 3.9812. Min Act: -0.1700
Data Index: 6985436 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2625. Min Range: -4.2625
Max Act: 3.9812. Min Act: -0.1700
Data Index: 4534476 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2625. Min Range: -4.2625
Max Act: 3.9812. Min Act: -0.1700
Data Index: 5764580 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2625. Min Range: -4.2625
Max Act: 3.9812. Min Act: -0.1700
Data Index: 7860233 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2625. Min Range: -4.2625
Max Act: 3.9812. Min Act: -0.1700
Data Index: 4047775 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2625. Min Range: -4.2625
Max Act: 3.9812. Min Act: -0.1700
Data Index: 6683411 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2625. Min Range: -4.2625
Max Act: 3.9812. Min Act: -0.1700
Data Index: 1092378 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2625. Min Range: -4.2625
Max Act: 3.9500. Min Act: -0.1700
Data Index: 7750953 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2625. Min Range: -4.2625
Max Act: 3.9500. Min Act: -0.1700
Data Index: 4164970 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #19