Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1537 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5801. Min Range: -6.5801
Max Act: 6.5801. Min Act: -0.1700
Data Index: 5378617 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5801. Min Range: -6.5801
Max Act: 6.4239. Min Act: -0.1700
Data Index: 5378622 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5801. Min Range: -6.5801
Max Act: 6.4551. Min Act: -0.1700
Data Index: 776537 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5801. Min Range: -6.5801
Max Act: 6.3614. Min Act: -0.1700
Data Index: 5557633 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5801. Min Range: -6.5801
Max Act: 6.2989. Min Act: -0.1700
Data Index: 5548833 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5801. Min Range: -6.5801
Max Act: 6.2676. Min Act: -0.1700
Data Index: 3170034 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5801. Min Range: -6.5801
Max Act: 6.2051. Min Act: -0.1700
Data Index: 4306576 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5801. Min Range: -6.5801
Max Act: 6.2364. Min Act: -0.1700
Data Index: 8480930 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5801. Min Range: -6.5801
Max Act: 6.2364. Min Act: -0.1700
Data Index: 8234506 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5801. Min Range: -6.5801
Max Act: 6.2051. Min Act: -0.1700
Data Index: 7395788 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5801. Min Range: -6.5801
Max Act: 6.2051. Min Act: -0.1700
Data Index: 1876868 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5801. Min Range: -6.5801
Max Act: 6.1739. Min Act: -0.1700
Data Index: 6146018 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5801. Min Range: -6.5801
Max Act: 6.1426. Min Act: -0.1700
Data Index: 3542616 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5801. Min Range: -6.5801
Max Act: 6.1426. Min Act: -0.1700
Data Index: 2560382 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5801. Min Range: -6.5801
Max Act: 6.1426. Min Act: -0.1700
Data Index: 7184196 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5801. Min Range: -6.5801
Max Act: 6.1426. Min Act: -0.1700
Data Index: 235310 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5801. Min Range: -6.5801
Max Act: 6.1114. Min Act: -0.1700
Data Index: 6239163 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5801. Min Range: -6.5801
Max Act: 6.1114. Min Act: -0.1700
Data Index: 1540113 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5801. Min Range: -6.5801
Max Act: 6.1114. Min Act: -0.1700
Data Index: 7064629 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5801. Min Range: -6.5801
Max Act: 6.0801. Min Act: -0.1700
Data Index: 6113053 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #19