Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3867 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4374. Min Range: -5.4374
Max Act: 5.4374. Min Act: -0.1700
Data Index: 929769 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4374. Min Range: -5.4374
Max Act: 5.2499. Min Act: -0.1700
Data Index: 6707470 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4374. Min Range: -5.4374
Max Act: 5.1874. Min Act: -0.1700
Data Index: 3966613 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4374. Min Range: -5.4374
Max Act: 5.1249. Min Act: -0.1700
Data Index: 2717977 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4374. Min Range: -5.4374
Max Act: 5.1249. Min Act: -0.1700
Data Index: 2602954 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4374. Min Range: -5.4374
Max Act: 5.0937. Min Act: -0.1700
Data Index: 7546429 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4374. Min Range: -5.4374
Max Act: 5.0624. Min Act: -0.1700
Data Index: 4527037 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4374. Min Range: -5.4374
Max Act: 4.9999. Min Act: -0.1700
Data Index: 1946538 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4374. Min Range: -5.4374
Max Act: 4.9999. Min Act: -0.1700
Data Index: 8571957 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4374. Min Range: -5.4374
Max Act: 4.9687. Min Act: -0.1700
Data Index: 1232687 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4374. Min Range: -5.4374
Max Act: 4.9687. Min Act: -0.1700
Data Index: 564623 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4374. Min Range: -5.4374
Max Act: 4.9374. Min Act: -0.1700
Data Index: 7146877 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4374. Min Range: -5.4374
Max Act: 4.9374. Min Act: -0.1700
Data Index: 4782911 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4374. Min Range: -5.4374
Max Act: 4.9062. Min Act: -0.1700
Data Index: 7258198 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4374. Min Range: -5.4374
Max Act: 4.9062. Min Act: -0.1700
Data Index: 6286041 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4374. Min Range: -5.4374
Max Act: 4.9062. Min Act: -0.1700
Data Index: 5157819 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4374. Min Range: -5.4374
Max Act: 4.9062. Min Act: -0.1700
Data Index: 3316426 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4374. Min Range: -5.4374
Max Act: 4.9062. Min Act: -0.1700
Data Index: 6701729 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4374. Min Range: -5.4374
Max Act: 4.8749. Min Act: -0.1700
Data Index: 640747 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4374. Min Range: -5.4374
Max Act: 4.8749. Min Act: -0.1700
Data Index: 3265727 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #19