Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3529 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9840. Min Range: -6.9840
Max Act: 6.9840. Min Act: -0.1700
Data Index: 1464710 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9840. Min Range: -6.9840
Max Act: 6.9215. Min Act: -0.1700
Data Index: 5098825 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9840. Min Range: -6.9840
Max Act: 6.8590. Min Act: -0.1700
Data Index: 2876088 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9840. Min Range: -6.9840
Max Act: 6.7965. Min Act: -0.1700
Data Index: 1516482 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9840. Min Range: -6.9840
Max Act: 6.7653. Min Act: -0.1700
Data Index: 1314261 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9840. Min Range: -6.9840
Max Act: 6.7340. Min Act: -0.1700
Data Index: 4239276 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9840. Min Range: -6.9840
Max Act: 6.7028. Min Act: -0.1700
Data Index: 252988 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9840. Min Range: -6.9840
Max Act: 6.6090. Min Act: -0.1700
Data Index: 8633620 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9840. Min Range: -6.9840
Max Act: 6.6090. Min Act: -0.1700
Data Index: 1591558 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9840. Min Range: -6.9840
Max Act: 6.6090. Min Act: -0.1700
Data Index: 6649968 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9840. Min Range: -6.9840
Max Act: 6.5778. Min Act: -0.1700
Data Index: 1619928 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9840. Min Range: -6.9840
Max Act: 6.5778. Min Act: -0.1700
Data Index: 4621942 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9840. Min Range: -6.9840
Max Act: 6.6090. Min Act: -0.1700
Data Index: 4173728 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9840. Min Range: -6.9840
Max Act: 6.5465. Min Act: -0.1700
Data Index: 474310 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9840. Min Range: -6.9840
Max Act: 6.5465. Min Act: -0.1700
Data Index: 3382197 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9840. Min Range: -6.9840
Max Act: 6.5153. Min Act: -0.1700
Data Index: 3939365 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9840. Min Range: -6.9840
Max Act: 6.5153. Min Act: -0.1700
Data Index: 5142013 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9840. Min Range: -6.9840
Max Act: 6.5153. Min Act: -0.1700
Data Index: 4320791 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9840. Min Range: -6.9840
Max Act: 6.4840. Min Act: -0.1700
Data Index: 991118 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9840. Min Range: -6.9840
Max Act: 6.5153. Min Act: -0.1700
Data Index: 201075 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #19