Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 463 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1288. Min Range: -6.1288
Max Act: 6.1288. Min Act: -0.1700
Data Index: 2258429 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1288. Min Range: -6.1288
Max Act: 6.0038. Min Act: -0.1700
Data Index: 8413333 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1288. Min Range: -6.1288
Max Act: 5.9725. Min Act: -0.1700
Data Index: 5052134 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1288. Min Range: -6.1288
Max Act: 5.9725. Min Act: -0.1700
Data Index: 4776199 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1288. Min Range: -6.1288
Max Act: 5.9413. Min Act: -0.1700
Data Index: 5896826 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1288. Min Range: -6.1288
Max Act: 5.9100. Min Act: -0.1700
Data Index: 5225525 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1288. Min Range: -6.1288
Max Act: 5.9100. Min Act: -0.1700
Data Index: 983233 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1288. Min Range: -6.1288
Max Act: 5.9100. Min Act: -0.1700
Data Index: 8701925 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1288. Min Range: -6.1288
Max Act: 5.8788. Min Act: -0.1700
Data Index: 2444915 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1288. Min Range: -6.1288
Max Act: 5.8788. Min Act: -0.1700
Data Index: 8749418 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1288. Min Range: -6.1288
Max Act: 5.8788. Min Act: -0.1700
Data Index: 4653152 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1288. Min Range: -6.1288
Max Act: 5.8475. Min Act: -0.1700
Data Index: 5291050 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1288. Min Range: -6.1288
Max Act: 5.8475. Min Act: -0.1700
Data Index: 3623890 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1288. Min Range: -6.1288
Max Act: 5.8163. Min Act: -0.1700
Data Index: 6274750 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1288. Min Range: -6.1288
Max Act: 5.8163. Min Act: -0.1700
Data Index: 4776197 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1288. Min Range: -6.1288
Max Act: 5.8163. Min Act: -0.1700
Data Index: 4204980 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1288. Min Range: -6.1288
Max Act: 5.8163. Min Act: -0.1700
Data Index: 7674320 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1288. Min Range: -6.1288
Max Act: 5.8163. Min Act: -0.1700
Data Index: 6454766 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1288. Min Range: -6.1288
Max Act: 5.7850. Min Act: -0.1700
Data Index: 983236 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1288. Min Range: -6.1288
Max Act: 5.7850. Min Act: -0.1700
Data Index: 5018001 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #19