Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5541 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1367. Min Range: -6.1367
Max Act: 6.1367. Min Act: -0.1700
Data Index: 5828372 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1367. Min Range: -6.1367
Max Act: 6.1055. Min Act: -0.1700
Data Index: 2285550 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1367. Min Range: -6.1367
Max Act: 6.0742. Min Act: -0.1700
Data Index: 6551206 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1367. Min Range: -6.1367
Max Act: 6.0430. Min Act: -0.1700
Data Index: 6165222 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1367. Min Range: -6.1367
Max Act: 5.9492. Min Act: -0.1700
Data Index: 6543906 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1367. Min Range: -6.1367
Max Act: 5.9492. Min Act: -0.1700
Data Index: 6996648 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1367. Min Range: -6.1367
Max Act: 5.9180. Min Act: -0.1700
Data Index: 5981080 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1367. Min Range: -6.1367
Max Act: 5.9180. Min Act: -0.1700
Data Index: 885166 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1367. Min Range: -6.1367
Max Act: 5.8867. Min Act: -0.1700
Data Index: 2856336 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1367. Min Range: -6.1367
Max Act: 5.8555. Min Act: -0.1700
Data Index: 3158325 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1367. Min Range: -6.1367
Max Act: 5.8555. Min Act: -0.1700
Data Index: 7677252 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1367. Min Range: -6.1367
Max Act: 5.8555. Min Act: -0.1700
Data Index: 5436152 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1367. Min Range: -6.1367
Max Act: 5.8555. Min Act: -0.1700
Data Index: 4463514 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1367. Min Range: -6.1367
Max Act: 5.8242. Min Act: -0.1700
Data Index: 2513463 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1367. Min Range: -6.1367
Max Act: 5.8242. Min Act: -0.1700
Data Index: 5981084 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1367. Min Range: -6.1367
Max Act: 5.7617. Min Act: -0.1700
Data Index: 6960949 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1367. Min Range: -6.1367
Max Act: 5.7617. Min Act: -0.1700
Data Index: 4752232 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1367. Min Range: -6.1367
Max Act: 5.7305. Min Act: -0.1700
Data Index: 98234 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1367. Min Range: -6.1367
Max Act: 5.6992. Min Act: -0.1700
Data Index: 1119637 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1367. Min Range: -6.1367
Max Act: 5.6992. Min Act: -0.1700
Data Index: 2922923 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #19