Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1442 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.9229. Min Range: -1.9229
Max Act: 1.9229. Min Act: -0.1700
Data Index: 4592187 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9229. Min Range: -1.9229
Max Act: 1.9229. Min Act: -0.1700
Data Index: 7703728 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9229. Min Range: -1.9229
Max Act: 1.9229. Min Act: -0.1700
Data Index: 109087 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9229. Min Range: -1.9229
Max Act: 1.9229. Min Act: -0.1700
Data Index: 1608849 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9229. Min Range: -1.9229
Max Act: 1.8888. Min Act: -0.1700
Data Index: 526107 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9229. Min Range: -1.9229
Max Act: 1.9059. Min Act: -0.1700
Data Index: 7224358 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9229. Min Range: -1.9229
Max Act: 1.9059. Min Act: -0.1700
Data Index: 6370648 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9229. Min Range: -1.9229
Max Act: 1.9059. Min Act: -0.1700
Data Index: 3120995 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9229. Min Range: -1.9229
Max Act: 1.8888. Min Act: -0.1700
Data Index: 8268738 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9229. Min Range: -1.9229
Max Act: 1.8888. Min Act: -0.1700
Data Index: 2758467 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9229. Min Range: -1.9229
Max Act: 1.8717. Min Act: -0.1700
Data Index: 4464221 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9229. Min Range: -1.9229
Max Act: 1.8888. Min Act: -0.1700
Data Index: 2875834 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9229. Min Range: -1.9229
Max Act: 1.8717. Min Act: -0.1700
Data Index: 2031769 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9229. Min Range: -1.9229
Max Act: 1.8717. Min Act: -0.1700
Data Index: 1172845 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9229. Min Range: -1.9229
Max Act: 1.8717. Min Act: -0.1700
Data Index: 3380691 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9229. Min Range: -1.9229
Max Act: 1.8717. Min Act: -0.1700
Data Index: 4729583 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9229. Min Range: -1.9229
Max Act: 1.8717. Min Act: -0.1700
Data Index: 2140778 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9229. Min Range: -1.9229
Max Act: 1.8717. Min Act: -0.1700
Data Index: 5648698 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9229. Min Range: -1.9229
Max Act: 1.8717. Min Act: -0.1700
Data Index: 7447304 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9229. Min Range: -1.9229
Max Act: 1.8717. Min Act: -0.1700
Data Index: 5968337 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #19