Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 623 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7920. Min Range: -4.7920
Max Act: 4.7920. Min Act: -0.1700
Data Index: 5880948 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7920. Min Range: -4.7920
Max Act: 4.7295. Min Act: -0.1700
Data Index: 8439170 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7920. Min Range: -4.7920
Max Act: 4.6983. Min Act: -0.1700
Data Index: 7752881 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7920. Min Range: -4.7920
Max Act: 4.6983. Min Act: -0.1700
Data Index: 4745042 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7920. Min Range: -4.7920
Max Act: 4.6983. Min Act: -0.1700
Data Index: 3767479 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7920. Min Range: -4.7920
Max Act: 4.6983. Min Act: -0.1700
Data Index: 4115656 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7920. Min Range: -4.7920
Max Act: 4.6983. Min Act: -0.1700
Data Index: 7875899 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7920. Min Range: -4.7920
Max Act: 4.6670. Min Act: -0.1700
Data Index: 2228964 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7920. Min Range: -4.7920
Max Act: 4.6670. Min Act: -0.1700
Data Index: 6801108 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7920. Min Range: -4.7920
Max Act: 4.6670. Min Act: -0.1700
Data Index: 4647873 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7920. Min Range: -4.7920
Max Act: 4.6670. Min Act: -0.1700
Data Index: 6665381 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7920. Min Range: -4.7920
Max Act: 4.6670. Min Act: -0.1700
Data Index: 7796920 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7920. Min Range: -4.7920
Max Act: 4.6670. Min Act: -0.1700
Data Index: 4252802 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7920. Min Range: -4.7920
Max Act: 4.6358. Min Act: -0.1700
Data Index: 1280547 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7920. Min Range: -4.7920
Max Act: 4.6358. Min Act: -0.1700
Data Index: 6581600 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7920. Min Range: -4.7920
Max Act: 4.6358. Min Act: -0.1700
Data Index: 6070571 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7920. Min Range: -4.7920
Max Act: 4.6358. Min Act: -0.1700
Data Index: 2054816 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7920. Min Range: -4.7920
Max Act: 4.6045. Min Act: -0.1700
Data Index: 2611468 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7920. Min Range: -4.7920
Max Act: 4.6045. Min Act: -0.1700
Data Index: 2411169 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7920. Min Range: -4.7920
Max Act: 4.6045. Min Act: -0.1700
Data Index: 7571903 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19