Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3050 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5124. Min Range: -5.5124
Max Act: 5.5124. Min Act: -0.1700
Data Index: 4077892 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5124. Min Range: -5.5124
Max Act: 5.4811. Min Act: -0.1700
Data Index: 4023155 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5124. Min Range: -5.5124
Max Act: 5.3561. Min Act: -0.1700
Data Index: 2752804 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5124. Min Range: -5.5124
Max Act: 5.2936. Min Act: -0.1700
Data Index: 7606888 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5124. Min Range: -5.5124
Max Act: 5.2936. Min Act: -0.1700
Data Index: 5637467 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5124. Min Range: -5.5124
Max Act: 5.2624. Min Act: -0.1700
Data Index: 458531 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5124. Min Range: -5.5124
Max Act: 5.2624. Min Act: -0.1700
Data Index: 1486747 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5124. Min Range: -5.5124
Max Act: 5.1999. Min Act: -0.1700
Data Index: 6629754 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5124. Min Range: -5.5124
Max Act: 5.1999. Min Act: -0.1700
Data Index: 2334995 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5124. Min Range: -5.5124
Max Act: 5.1999. Min Act: -0.1700
Data Index: 7061328 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5124. Min Range: -5.5124
Max Act: 5.1999. Min Act: -0.1700
Data Index: 4277102 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5124. Min Range: -5.5124
Max Act: 5.1686. Min Act: -0.1700
Data Index: 7245817 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5124. Min Range: -5.5124
Max Act: 5.1686. Min Act: -0.1700
Data Index: 5644643 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5124. Min Range: -5.5124
Max Act: 5.1686. Min Act: -0.1700
Data Index: 3295788 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5124. Min Range: -5.5124
Max Act: 5.1999. Min Act: -0.1700
Data Index: 4283508 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5124. Min Range: -5.5124
Max Act: 5.1686. Min Act: -0.1700
Data Index: 8622951 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5124. Min Range: -5.5124
Max Act: 5.1999. Min Act: -0.1700
Data Index: 578728 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5124. Min Range: -5.5124
Max Act: 5.1374. Min Act: -0.1700
Data Index: 6931436 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5124. Min Range: -5.5124
Max Act: 5.1374. Min Act: -0.1700
Data Index: 5718696 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5124. Min Range: -5.5124
Max Act: 5.1686. Min Act: -0.1700
Data Index: 6647375 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #19