Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 914 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7000. Min Range: -7.7000
Max Act: 7.7000. Min Act: -0.1700
Data Index: 1275408 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7000. Min Range: -7.7000
Max Act: 7.5750. Min Act: -0.1700
Data Index: 6892411 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7000. Min Range: -7.7000
Max Act: 7.4500. Min Act: -0.1700
Data Index: 5260234 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7000. Min Range: -7.7000
Max Act: 7.4500. Min Act: -0.1700
Data Index: 6760925 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7000. Min Range: -7.7000
Max Act: 7.4187. Min Act: -0.1700
Data Index: 1948567 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7000. Min Range: -7.7000
Max Act: 7.4187. Min Act: -0.1700
Data Index: 5539332 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7000. Min Range: -7.7000
Max Act: 7.3562. Min Act: -0.1700
Data Index: 3792012 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7000. Min Range: -7.7000
Max Act: 7.3875. Min Act: -0.1700
Data Index: 6702931 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7000. Min Range: -7.7000
Max Act: 7.2625. Min Act: -0.1700
Data Index: 8183912 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7000. Min Range: -7.7000
Max Act: 7.2937. Min Act: -0.1700
Data Index: 8146155 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7000. Min Range: -7.7000
Max Act: 7.2625. Min Act: -0.1700
Data Index: 7408110 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7000. Min Range: -7.7000
Max Act: 7.2312. Min Act: -0.1700
Data Index: 4437782 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7000. Min Range: -7.7000
Max Act: 7.2312. Min Act: -0.1700
Data Index: 4406456 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7000. Min Range: -7.7000
Max Act: 7.2000. Min Act: -0.1700
Data Index: 2931600 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7000. Min Range: -7.7000
Max Act: 7.1687. Min Act: -0.1700
Data Index: 7950306 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7000. Min Range: -7.7000
Max Act: 7.2000. Min Act: -0.1700
Data Index: 6225856 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7000. Min Range: -7.7000
Max Act: 7.2000. Min Act: -0.1700
Data Index: 8121499 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7000. Min Range: -7.7000
Max Act: 7.2000. Min Act: -0.1700
Data Index: 8281693 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7000. Min Range: -7.7000
Max Act: 7.1687. Min Act: -0.1700
Data Index: 998552 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7000. Min Range: -7.7000
Max Act: 7.1375. Min Act: -0.1700
Data Index: 1896643 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #19