Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2640 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8722. Min Range: -6.8722
Max Act: 6.8722. Min Act: -0.1700
Data Index: 1514373 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8722. Min Range: -6.8722
Max Act: 6.8097. Min Act: -0.1700
Data Index: 8458305 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8722. Min Range: -6.8722
Max Act: 6.8097. Min Act: -0.1700
Data Index: 8529939 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8722. Min Range: -6.8722
Max Act: 6.6222. Min Act: -0.1700
Data Index: 7225155 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8722. Min Range: -6.8722
Max Act: 6.5284. Min Act: -0.1700
Data Index: 7623720 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8722. Min Range: -6.8722
Max Act: 6.5284. Min Act: -0.1700
Data Index: 3455901 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8722. Min Range: -6.8722
Max Act: 6.4659. Min Act: -0.1700
Data Index: 6036143 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8722. Min Range: -6.8722
Max Act: 6.4659. Min Act: -0.1700
Data Index: 8740131 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8722. Min Range: -6.8722
Max Act: 6.4347. Min Act: -0.1700
Data Index: 1282641 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8722. Min Range: -6.8722
Max Act: 6.3722. Min Act: -0.1700
Data Index: 7590765 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8722. Min Range: -6.8722
Max Act: 6.3722. Min Act: -0.1700
Data Index: 7743513 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8722. Min Range: -6.8722
Max Act: 6.3722. Min Act: -0.1700
Data Index: 3963845 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8722. Min Range: -6.8722
Max Act: 6.3722. Min Act: -0.1700
Data Index: 6583785 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8722. Min Range: -6.8722
Max Act: 6.3409. Min Act: -0.1700
Data Index: 1546649 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8722. Min Range: -6.8722
Max Act: 6.3409. Min Act: -0.1700
Data Index: 8558868 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8722. Min Range: -6.8722
Max Act: 6.3409. Min Act: -0.1700
Data Index: 4689731 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8722. Min Range: -6.8722
Max Act: 6.3409. Min Act: -0.1700
Data Index: 6090332 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8722. Min Range: -6.8722
Max Act: 6.3409. Min Act: -0.1700
Data Index: 486530 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8722. Min Range: -6.8722
Max Act: 6.3097. Min Act: -0.1700
Data Index: 3153506 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8722. Min Range: -6.8722
Max Act: 6.3097. Min Act: -0.1700
Data Index: 7967666 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #19