Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5927 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0216. Min Range: -5.0216
Max Act: 5.0216. Min Act: -0.1700
Data Index: 1983746 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0216. Min Range: -5.0216
Max Act: 4.8653. Min Act: -0.1700
Data Index: 498183 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0216. Min Range: -5.0216
Max Act: 4.8341. Min Act: -0.1700
Data Index: 4459241 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0216. Min Range: -5.0216
Max Act: 4.8341. Min Act: -0.1700
Data Index: 6056276 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0216. Min Range: -5.0216
Max Act: 4.8028. Min Act: -0.1700
Data Index: 4030673 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0216. Min Range: -5.0216
Max Act: 4.6778. Min Act: -0.1700
Data Index: 6462207 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0216. Min Range: -5.0216
Max Act: 4.6466. Min Act: -0.1700
Data Index: 3918610 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0216. Min Range: -5.0216
Max Act: 4.6153. Min Act: -0.1700
Data Index: 734088 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0216. Min Range: -5.0216
Max Act: 4.6466. Min Act: -0.1700
Data Index: 3657539 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0216. Min Range: -5.0216
Max Act: 4.6466. Min Act: -0.1700
Data Index: 5989078 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0216. Min Range: -5.0216
Max Act: 4.6153. Min Act: -0.1700
Data Index: 889639 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0216. Min Range: -5.0216
Max Act: 4.5841. Min Act: -0.1700
Data Index: 4722155 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0216. Min Range: -5.0216
Max Act: 4.5841. Min Act: -0.1700
Data Index: 8714746 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0216. Min Range: -5.0216
Max Act: 4.5528. Min Act: -0.1700
Data Index: 3823224 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0216. Min Range: -5.0216
Max Act: 4.5216. Min Act: -0.1700
Data Index: 5216987 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0216. Min Range: -5.0216
Max Act: 4.5528. Min Act: -0.1700
Data Index: 5488965 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0216. Min Range: -5.0216
Max Act: 4.5216. Min Act: -0.1700
Data Index: 1065080 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0216. Min Range: -5.0216
Max Act: 4.5216. Min Act: -0.1700
Data Index: 633159 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0216. Min Range: -5.0216
Max Act: 4.5528. Min Act: -0.1700
Data Index: 5543179 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0216. Min Range: -5.0216
Max Act: 4.4903. Min Act: -0.1700
Data Index: 852110 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #19