Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3274 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3370. Min Range: -4.3370
Max Act: 4.3370. Min Act: -0.1700
Data Index: 8022111 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3370. Min Range: -4.3370
Max Act: 4.3370. Min Act: -0.1700
Data Index: 6050723 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3370. Min Range: -4.3370
Max Act: 4.2745. Min Act: -0.1700
Data Index: 2974815 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3370. Min Range: -4.3370
Max Act: 4.2433. Min Act: -0.1700
Data Index: 5220921 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3370. Min Range: -4.3370
Max Act: 4.2120. Min Act: -0.1700
Data Index: 2078519 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3370. Min Range: -4.3370
Max Act: 4.2120. Min Act: -0.1700
Data Index: 6319808 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3370. Min Range: -4.3370
Max Act: 4.1808. Min Act: -0.1700
Data Index: 2185271 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3370. Min Range: -4.3370
Max Act: 4.1808. Min Act: -0.1700
Data Index: 3490361 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3370. Min Range: -4.3370
Max Act: 4.1495. Min Act: -0.1700
Data Index: 2058942 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3370. Min Range: -4.3370
Max Act: 4.1495. Min Act: -0.1700
Data Index: 478483 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3370. Min Range: -4.3370
Max Act: 4.1495. Min Act: -0.1700
Data Index: 2515461 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3370. Min Range: -4.3370
Max Act: 4.1183. Min Act: -0.1700
Data Index: 1642926 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3370. Min Range: -4.3370
Max Act: 4.0870. Min Act: -0.1700
Data Index: 5407122 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3370. Min Range: -4.3370
Max Act: 4.0870. Min Act: -0.1700
Data Index: 2623492 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3370. Min Range: -4.3370
Max Act: 4.0870. Min Act: -0.1700
Data Index: 2390567 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3370. Min Range: -4.3370
Max Act: 4.0870. Min Act: -0.1700
Data Index: 162905 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3370. Min Range: -4.3370
Max Act: 4.0870. Min Act: -0.1700
Data Index: 8513530 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3370. Min Range: -4.3370
Max Act: 4.0558. Min Act: -0.1700
Data Index: 2337572 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3370. Min Range: -4.3370
Max Act: 4.0558. Min Act: -0.1700
Data Index: 3625626 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3370. Min Range: -4.3370
Max Act: 4.0558. Min Act: -0.1700
Data Index: 701495 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #19