Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3097 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2946. Min Range: -7.2946
Max Act: 7.2946. Min Act: -0.1700
Data Index: 1839391 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2946. Min Range: -7.2946
Max Act: 7.1384. Min Act: -0.1700
Data Index: 2546003 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2946. Min Range: -7.2946
Max Act: 7.1071. Min Act: -0.1700
Data Index: 8152970 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2946. Min Range: -7.2946
Max Act: 7.0446. Min Act: -0.1700
Data Index: 3800815 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2946. Min Range: -7.2946
Max Act: 7.0446. Min Act: -0.1700
Data Index: 8005446 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2946. Min Range: -7.2946
Max Act: 6.9509. Min Act: -0.1700
Data Index: 6429363 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2946. Min Range: -7.2946
Max Act: 6.8571. Min Act: -0.1700
Data Index: 3892602 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2946. Min Range: -7.2946
Max Act: 6.8571. Min Act: -0.1700
Data Index: 511128 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2946. Min Range: -7.2946
Max Act: 6.8259. Min Act: -0.1700
Data Index: 3320107 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2946. Min Range: -7.2946
Max Act: 6.8259. Min Act: -0.1700
Data Index: 6312702 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2946. Min Range: -7.2946
Max Act: 6.7634. Min Act: -0.1700
Data Index: 7962037 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2946. Min Range: -7.2946
Max Act: 6.7946. Min Act: -0.1700
Data Index: 4647311 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2946. Min Range: -7.2946
Max Act: 6.7946. Min Act: -0.1700
Data Index: 534702 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2946. Min Range: -7.2946
Max Act: 6.7634. Min Act: -0.1700
Data Index: 8116006 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2946. Min Range: -7.2946
Max Act: 6.7634. Min Act: -0.1700
Data Index: 2902088 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2946. Min Range: -7.2946
Max Act: 6.7009. Min Act: -0.1700
Data Index: 8157976 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2946. Min Range: -7.2946
Max Act: 6.7321. Min Act: -0.1700
Data Index: 723413 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2946. Min Range: -7.2946
Max Act: 6.7009. Min Act: -0.1700
Data Index: 475000 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2946. Min Range: -7.2946
Max Act: 6.7009. Min Act: -0.1700
Data Index: 3754704 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2946. Min Range: -7.2946
Max Act: 6.7009. Min Act: -0.1700
Data Index: 349674 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19