Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1824 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0781. Min Range: -6.0781
Max Act: 6.0781. Min Act: -0.1700
Data Index: 8187300 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0781. Min Range: -6.0781
Max Act: 6.0781. Min Act: -0.1700
Data Index: 4607758 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0781. Min Range: -6.0781
Max Act: 6.0156. Min Act: -0.1700
Data Index: 2759747 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0781. Min Range: -6.0781
Max Act: 5.9844. Min Act: -0.1700
Data Index: 5311768 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0781. Min Range: -6.0781
Max Act: 5.9844. Min Act: -0.1700
Data Index: 8485564 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0781. Min Range: -6.0781
Max Act: 5.9219. Min Act: -0.1700
Data Index: 6431121 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0781. Min Range: -6.0781
Max Act: 5.8906. Min Act: -0.1700
Data Index: 7662782 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0781. Min Range: -6.0781
Max Act: 5.8281. Min Act: -0.1700
Data Index: 4476629 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0781. Min Range: -6.0781
Max Act: 5.7969. Min Act: -0.1700
Data Index: 5388524 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0781. Min Range: -6.0781
Max Act: 5.8281. Min Act: -0.1700
Data Index: 8322135 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0781. Min Range: -6.0781
Max Act: 5.7656. Min Act: -0.1700
Data Index: 5079636 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0781. Min Range: -6.0781
Max Act: 5.7344. Min Act: -0.1700
Data Index: 3148996 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0781. Min Range: -6.0781
Max Act: 5.7344. Min Act: -0.1700
Data Index: 3853566 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0781. Min Range: -6.0781
Max Act: 5.7031. Min Act: -0.1700
Data Index: 1591107 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0781. Min Range: -6.0781
Max Act: 5.7344. Min Act: -0.1700
Data Index: 2051412 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0781. Min Range: -6.0781
Max Act: 5.7031. Min Act: -0.1700
Data Index: 7495602 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0781. Min Range: -6.0781
Max Act: 5.7031. Min Act: -0.1700
Data Index: 2509815 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0781. Min Range: -6.0781
Max Act: 5.6719. Min Act: -0.1700
Data Index: 5525610 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0781. Min Range: -6.0781
Max Act: 5.6719. Min Act: -0.1700
Data Index: 6944250 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0781. Min Range: -6.0781
Max Act: 5.6719. Min Act: -0.1700
Data Index: 682807 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #19