Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2722 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0709. Min Range: -6.0709
Max Act: 6.0709. Min Act: -0.1700
Data Index: 83881 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0709. Min Range: -6.0709
Max Act: 6.0396. Min Act: -0.1700
Data Index: 7786743 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0709. Min Range: -6.0709
Max Act: 6.0084. Min Act: -0.1700
Data Index: 83882 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0709. Min Range: -6.0709
Max Act: 6.0084. Min Act: -0.1700
Data Index: 1461447 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0709. Min Range: -6.0709
Max Act: 6.0084. Min Act: -0.1700
Data Index: 6560926 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0709. Min Range: -6.0709
Max Act: 6.0084. Min Act: -0.1700
Data Index: 3079151 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0709. Min Range: -6.0709
Max Act: 5.9771. Min Act: -0.1700
Data Index: 1779053 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0709. Min Range: -6.0709
Max Act: 5.9771. Min Act: -0.1700
Data Index: 5847160 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0709. Min Range: -6.0709
Max Act: 5.9771. Min Act: -0.1700
Data Index: 6754939 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0709. Min Range: -6.0709
Max Act: 5.9459. Min Act: -0.1700
Data Index: 2411442 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0709. Min Range: -6.0709
Max Act: 5.9459. Min Act: -0.1700
Data Index: 3859219 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0709. Min Range: -6.0709
Max Act: 5.9459. Min Act: -0.1700
Data Index: 88700 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0709. Min Range: -6.0709
Max Act: 5.9459. Min Act: -0.1700
Data Index: 3676839 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0709. Min Range: -6.0709
Max Act: 5.9459. Min Act: -0.1700
Data Index: 4855716 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0709. Min Range: -6.0709
Max Act: 5.9146. Min Act: -0.1700
Data Index: 3617569 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0709. Min Range: -6.0709
Max Act: 5.9146. Min Act: -0.1700
Data Index: 6585714 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0709. Min Range: -6.0709
Max Act: 5.9146. Min Act: -0.1700
Data Index: 3531831 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0709. Min Range: -6.0709
Max Act: 5.9146. Min Act: -0.1700
Data Index: 1042398 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0709. Min Range: -6.0709
Max Act: 5.9146. Min Act: -0.1700
Data Index: 7568143 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0709. Min Range: -6.0709
Max Act: 5.9146. Min Act: -0.1700
Data Index: 1138110 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19