Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6125 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9823. Min Range: -5.9823
Max Act: 5.9823. Min Act: -0.1700
Data Index: 406012 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9823. Min Range: -5.9823
Max Act: 5.9823. Min Act: -0.1700
Data Index: 5785498 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9823. Min Range: -5.9823
Max Act: 5.9198. Min Act: -0.1700
Data Index: 1356580 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9823. Min Range: -5.9823
Max Act: 5.8885. Min Act: -0.1700
Data Index: 7783456 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9823. Min Range: -5.9823
Max Act: 5.9198. Min Act: -0.1700
Data Index: 8319908 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9823. Min Range: -5.9823
Max Act: 5.8260. Min Act: -0.1700
Data Index: 5520417 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9823. Min Range: -5.9823
Max Act: 5.7635. Min Act: -0.1700
Data Index: 4015884 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9823. Min Range: -5.9823
Max Act: 5.7323. Min Act: -0.1700
Data Index: 3078421 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9823. Min Range: -5.9823
Max Act: 5.7010. Min Act: -0.1700
Data Index: 6106127 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9823. Min Range: -5.9823
Max Act: 5.7010. Min Act: -0.1700
Data Index: 8264343 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9823. Min Range: -5.9823
Max Act: 5.6698. Min Act: -0.1700
Data Index: 3124692 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9823. Min Range: -5.9823
Max Act: 5.5760. Min Act: -0.1700
Data Index: 8311366 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9823. Min Range: -5.9823
Max Act: 5.6073. Min Act: -0.1700
Data Index: 432113 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9823. Min Range: -5.9823
Max Act: 5.6073. Min Act: -0.1700
Data Index: 1646222 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9823. Min Range: -5.9823
Max Act: 5.5448. Min Act: -0.1700
Data Index: 100434 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9823. Min Range: -5.9823
Max Act: 5.5448. Min Act: -0.1700
Data Index: 3647386 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9823. Min Range: -5.9823
Max Act: 5.5448. Min Act: -0.1700
Data Index: 717728 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9823. Min Range: -5.9823
Max Act: 5.5448. Min Act: -0.1700
Data Index: 2200308 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9823. Min Range: -5.9823
Max Act: 5.5135. Min Act: -0.1700
Data Index: 6784748 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9823. Min Range: -5.9823
Max Act: 5.5135. Min Act: -0.1700
Data Index: 1740828 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #19