Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4923 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3617. Min Range: -8.3617
Max Act: 8.3617. Min Act: -0.1700
Data Index: 606868 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3617. Min Range: -8.3617
Max Act: 8.2992. Min Act: -0.1700
Data Index: 1723505 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3617. Min Range: -8.3617
Max Act: 8.2367. Min Act: -0.1700
Data Index: 2036464 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3617. Min Range: -8.3617
Max Act: 8.0492. Min Act: -0.1700
Data Index: 8123083 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3617. Min Range: -8.3617
Max Act: 7.9867. Min Act: -0.1700
Data Index: 6737609 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3617. Min Range: -8.3617
Max Act: 7.9867. Min Act: -0.1700
Data Index: 3533747 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3617. Min Range: -8.3617
Max Act: 7.9867. Min Act: -0.1700
Data Index: 3613302 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3617. Min Range: -8.3617
Max Act: 7.9242. Min Act: -0.1700
Data Index: 449328 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3617. Min Range: -8.3617
Max Act: 7.9242. Min Act: -0.1700
Data Index: 7881091 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3617. Min Range: -8.3617
Max Act: 7.7992. Min Act: -0.1700
Data Index: 347154 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3617. Min Range: -8.3617
Max Act: 7.7992. Min Act: -0.1700
Data Index: 1890007 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3617. Min Range: -8.3617
Max Act: 7.7680. Min Act: -0.1700
Data Index: 8098674 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3617. Min Range: -8.3617
Max Act: 7.7680. Min Act: -0.1700
Data Index: 7642085 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3617. Min Range: -8.3617
Max Act: 7.7680. Min Act: -0.1700
Data Index: 7080070 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3617. Min Range: -8.3617
Max Act: 7.7367. Min Act: -0.1700
Data Index: 7186561 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3617. Min Range: -8.3617
Max Act: 7.7367. Min Act: -0.1700
Data Index: 8434565 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3617. Min Range: -8.3617
Max Act: 7.7367. Min Act: -0.1700
Data Index: 8153495 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3617. Min Range: -8.3617
Max Act: 7.7367. Min Act: -0.1700
Data Index: 6290531 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3617. Min Range: -8.3617
Max Act: 7.7055. Min Act: -0.1700
Data Index: 7524313 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3617. Min Range: -8.3617
Max Act: 7.6742. Min Act: -0.1700
Data Index: 483004 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #19