Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5754 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5965. Min Range: -8.5965
Max Act: 8.5340. Min Act: -0.1700
Data Index: 4916846 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5965. Min Range: -8.5965
Max Act: 8.5965. Min Act: -0.1700
Data Index: 2703988 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5965. Min Range: -8.5965
Max Act: 8.1590. Min Act: -0.1700
Data Index: 6224569 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5965. Min Range: -8.5965
Max Act: 8.1590. Min Act: -0.1700
Data Index: 3509595 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5965. Min Range: -8.5965
Max Act: 8.0965. Min Act: -0.1700
Data Index: 5556304 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5965. Min Range: -8.5965
Max Act: 8.0340. Min Act: -0.1700
Data Index: 7768362 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5965. Min Range: -8.5965
Max Act: 7.9715. Min Act: -0.1700
Data Index: 98791 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5965. Min Range: -8.5965
Max Act: 7.9090. Min Act: -0.1700
Data Index: 1766746 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5965. Min Range: -8.5965
Max Act: 7.9090. Min Act: -0.1700
Data Index: 5455335 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5965. Min Range: -8.5965
Max Act: 7.9090. Min Act: -0.1700
Data Index: 8023324 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5965. Min Range: -8.5965
Max Act: 7.8778. Min Act: -0.1700
Data Index: 8093916 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5965. Min Range: -8.5965
Max Act: 7.8778. Min Act: -0.1700
Data Index: 5940865 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5965. Min Range: -8.5965
Max Act: 7.8778. Min Act: -0.1700
Data Index: 5898788 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5965. Min Range: -8.5965
Max Act: 7.7840. Min Act: -0.1700
Data Index: 7760915 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5965. Min Range: -8.5965
Max Act: 7.7528. Min Act: -0.1700
Data Index: 8126728 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5965. Min Range: -8.5965
Max Act: 7.7528. Min Act: -0.1700
Data Index: 1293269 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5965. Min Range: -8.5965
Max Act: 7.7840. Min Act: -0.1700
Data Index: 7534620 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5965. Min Range: -8.5965
Max Act: 7.7528. Min Act: -0.1700
Data Index: 2987765 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5965. Min Range: -8.5965
Max Act: 7.7528. Min Act: -0.1700
Data Index: 8753323 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5965. Min Range: -8.5965
Max Act: 7.7215. Min Act: -0.1700
Data Index: 2845670 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #19