Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1345 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7332. Min Range: -5.7332
Max Act: 5.7332. Min Act: -0.1700
Data Index: 3560468 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7332. Min Range: -5.7332
Max Act: 5.7332. Min Act: -0.1700
Data Index: 5906858 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7332. Min Range: -5.7332
Max Act: 5.7019. Min Act: -0.1700
Data Index: 900936 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7332. Min Range: -5.7332
Max Act: 5.6394. Min Act: -0.1700
Data Index: 5153755 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7332. Min Range: -5.7332
Max Act: 5.6707. Min Act: -0.1700
Data Index: 900941 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7332. Min Range: -5.7332
Max Act: 5.6707. Min Act: -0.1700
Data Index: 5153750 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7332. Min Range: -5.7332
Max Act: 5.6082. Min Act: -0.1700
Data Index: 3605305 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7332. Min Range: -5.7332
Max Act: 5.6394. Min Act: -0.1700
Data Index: 28524 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7332. Min Range: -5.7332
Max Act: 5.6082. Min Act: -0.1700
Data Index: 4742642 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7332. Min Range: -5.7332
Max Act: 5.6394. Min Act: -0.1700
Data Index: 4951650 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7332. Min Range: -5.7332
Max Act: 5.6082. Min Act: -0.1700
Data Index: 28537 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7332. Min Range: -5.7332
Max Act: 5.6082. Min Act: -0.1700
Data Index: 8653805 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7332. Min Range: -5.7332
Max Act: 5.6082. Min Act: -0.1700
Data Index: 4742663 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7332. Min Range: -5.7332
Max Act: 5.6082. Min Act: -0.1700
Data Index: 784673 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7332. Min Range: -5.7332
Max Act: 5.6082. Min Act: -0.1700
Data Index: 3381163 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7332. Min Range: -5.7332
Max Act: 5.6082. Min Act: -0.1700
Data Index: 4951646 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7332. Min Range: -5.7332
Max Act: 5.5769. Min Act: -0.1700
Data Index: 784701 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7332. Min Range: -5.7332
Max Act: 5.5769. Min Act: -0.1700
Data Index: 1606646 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7332. Min Range: -5.7332
Max Act: 5.5769. Min Act: -0.1700
Data Index: 2039525 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7332. Min Range: -5.7332
Max Act: 5.5769. Min Act: -0.1700
Data Index: 3094833 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #19