Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3421 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5472. Min Range: -6.5472
Max Act: 6.5472. Min Act: -0.1700
Data Index: 1577582 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5472. Min Range: -6.5472
Max Act: 6.2659. Min Act: -0.1700
Data Index: 3377227 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5472. Min Range: -6.5472
Max Act: 6.2659. Min Act: -0.1700
Data Index: 4844279 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5472. Min Range: -6.5472
Max Act: 6.2659. Min Act: -0.1700
Data Index: 3514031 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5472. Min Range: -6.5472
Max Act: 6.2034. Min Act: -0.1700
Data Index: 7727580 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5472. Min Range: -6.5472
Max Act: 6.1722. Min Act: -0.1700
Data Index: 4523510 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5472. Min Range: -6.5472
Max Act: 6.1722. Min Act: -0.1700
Data Index: 6953809 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5472. Min Range: -6.5472
Max Act: 6.1409. Min Act: -0.1700
Data Index: 2439074 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5472. Min Range: -6.5472
Max Act: 6.1409. Min Act: -0.1700
Data Index: 8616106 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5472. Min Range: -6.5472
Max Act: 6.1409. Min Act: -0.1700
Data Index: 7101362 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5472. Min Range: -6.5472
Max Act: 6.0784. Min Act: -0.1700
Data Index: 763512 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5472. Min Range: -6.5472
Max Act: 6.0472. Min Act: -0.1700
Data Index: 8426175 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5472. Min Range: -6.5472
Max Act: 6.0472. Min Act: -0.1700
Data Index: 2602443 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5472. Min Range: -6.5472
Max Act: 6.0472. Min Act: -0.1700
Data Index: 8532394 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5472. Min Range: -6.5472
Max Act: 6.0159. Min Act: -0.1700
Data Index: 5295565 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5472. Min Range: -6.5472
Max Act: 6.0159. Min Act: -0.1700
Data Index: 45930 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5472. Min Range: -6.5472
Max Act: 6.0159. Min Act: -0.1700
Data Index: 2784582 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5472. Min Range: -6.5472
Max Act: 5.9847. Min Act: -0.1700
Data Index: 4611803 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5472. Min Range: -6.5472
Max Act: 6.0159. Min Act: -0.1700
Data Index: 3437721 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5472. Min Range: -6.5472
Max Act: 5.9534. Min Act: -0.1700
Data Index: 3758890 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #19