Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3893 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3164. Min Range: -7.3164
Max Act: 7.3164. Min Act: -0.1700
Data Index: 5972307 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3164. Min Range: -7.3164
Max Act: 7.2539. Min Act: -0.1700
Data Index: 7194806 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3164. Min Range: -7.3164
Max Act: 7.1602. Min Act: -0.1700
Data Index: 46097 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3164. Min Range: -7.3164
Max Act: 7.0977. Min Act: -0.1700
Data Index: 1207240 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3164. Min Range: -7.3164
Max Act: 7.0352. Min Act: -0.1700
Data Index: 6492683 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3164. Min Range: -7.3164
Max Act: 6.9102. Min Act: -0.1700
Data Index: 1460548 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3164. Min Range: -7.3164
Max Act: 6.9102. Min Act: -0.1700
Data Index: 3852576 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3164. Min Range: -7.3164
Max Act: 6.8789. Min Act: -0.1700
Data Index: 535493 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3164. Min Range: -7.3164
Max Act: 6.8789. Min Act: -0.1700
Data Index: 7717108 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3164. Min Range: -7.3164
Max Act: 6.8789. Min Act: -0.1700
Data Index: 3139562 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3164. Min Range: -7.3164
Max Act: 6.8789. Min Act: -0.1700
Data Index: 1382905 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3164. Min Range: -7.3164
Max Act: 6.8477. Min Act: -0.1700
Data Index: 4665691 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3164. Min Range: -7.3164
Max Act: 6.8477. Min Act: -0.1700
Data Index: 2434184 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3164. Min Range: -7.3164
Max Act: 6.8477. Min Act: -0.1700
Data Index: 5483079 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3164. Min Range: -7.3164
Max Act: 6.8164. Min Act: -0.1700
Data Index: 113195 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3164. Min Range: -7.3164
Max Act: 6.8164. Min Act: -0.1700
Data Index: 1549458 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3164. Min Range: -7.3164
Max Act: 6.8164. Min Act: -0.1700
Data Index: 7243343 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3164. Min Range: -7.3164
Max Act: 6.7852. Min Act: -0.1700
Data Index: 2185610 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3164. Min Range: -7.3164
Max Act: 6.7852. Min Act: -0.1700
Data Index: 3523885 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3164. Min Range: -7.3164
Max Act: 6.7227. Min Act: -0.1700
Data Index: 3606460 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #19