Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3150 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0463. Min Range: -7.0463
Max Act: 7.0463. Min Act: -0.1700
Data Index: 2203592 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0463. Min Range: -7.0463
Max Act: 7.0151. Min Act: -0.1700
Data Index: 85448 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0463. Min Range: -7.0463
Max Act: 6.8901. Min Act: -0.1700
Data Index: 2801686 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0463. Min Range: -7.0463
Max Act: 6.7651. Min Act: -0.1700
Data Index: 6226046 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0463. Min Range: -7.0463
Max Act: 6.6713. Min Act: -0.1700
Data Index: 1957792 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0463. Min Range: -7.0463
Max Act: 6.6713. Min Act: -0.1700
Data Index: 4849427 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0463. Min Range: -7.0463
Max Act: 6.6401. Min Act: -0.1700
Data Index: 8324414 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0463. Min Range: -7.0463
Max Act: 6.5776. Min Act: -0.1700
Data Index: 5444339 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0463. Min Range: -7.0463
Max Act: 6.6088. Min Act: -0.1700
Data Index: 8362570 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0463. Min Range: -7.0463
Max Act: 6.5463. Min Act: -0.1700
Data Index: 7734465 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0463. Min Range: -7.0463
Max Act: 6.5776. Min Act: -0.1700
Data Index: 986673 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0463. Min Range: -7.0463
Max Act: 6.5463. Min Act: -0.1700
Data Index: 6925698 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0463. Min Range: -7.0463
Max Act: 6.5463. Min Act: -0.1700
Data Index: 7038434 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0463. Min Range: -7.0463
Max Act: 6.4838. Min Act: -0.1700
Data Index: 5008212 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0463. Min Range: -7.0463
Max Act: 6.5463. Min Act: -0.1700
Data Index: 8410082 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0463. Min Range: -7.0463
Max Act: 6.5151. Min Act: -0.1700
Data Index: 7749634 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0463. Min Range: -7.0463
Max Act: 6.4838. Min Act: -0.1700
Data Index: 8379128 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0463. Min Range: -7.0463
Max Act: 6.4526. Min Act: -0.1700
Data Index: 8724024 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0463. Min Range: -7.0463
Max Act: 6.4526. Min Act: -0.1700
Data Index: 2545767 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0463. Min Range: -7.0463
Max Act: 6.4838. Min Act: -0.1700
Data Index: 2347668 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #19