Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1949 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9244. Min Range: -5.9244
Max Act: 5.9244. Min Act: -0.1700
Data Index: 3390138 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9244. Min Range: -5.9244
Max Act: 5.8307. Min Act: -0.1700
Data Index: 3390137 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9244. Min Range: -5.9244
Max Act: 5.7682. Min Act: -0.1700
Data Index: 1110377 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9244. Min Range: -5.9244
Max Act: 5.7682. Min Act: -0.1700
Data Index: 1035823 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9244. Min Range: -5.9244
Max Act: 5.7369. Min Act: -0.1700
Data Index: 5444756 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9244. Min Range: -5.9244
Max Act: 5.7057. Min Act: -0.1700
Data Index: 2357064 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9244. Min Range: -5.9244
Max Act: 5.7057. Min Act: -0.1700
Data Index: 926007 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9244. Min Range: -5.9244
Max Act: 5.6744. Min Act: -0.1700
Data Index: 1874358 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9244. Min Range: -5.9244
Max Act: 5.6744. Min Act: -0.1700
Data Index: 4297656 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9244. Min Range: -5.9244
Max Act: 5.6432. Min Act: -0.1700
Data Index: 798973 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9244. Min Range: -5.9244
Max Act: 5.6432. Min Act: -0.1700
Data Index: 2983943 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9244. Min Range: -5.9244
Max Act: 5.6119. Min Act: -0.1700
Data Index: 3729387 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9244. Min Range: -5.9244
Max Act: 5.5807. Min Act: -0.1700
Data Index: 4138779 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9244. Min Range: -5.9244
Max Act: 5.5807. Min Act: -0.1700
Data Index: 1341648 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9244. Min Range: -5.9244
Max Act: 5.5494. Min Act: -0.1700
Data Index: 8698229 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9244. Min Range: -5.9244
Max Act: 5.5494. Min Act: -0.1700
Data Index: 1055029 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9244. Min Range: -5.9244
Max Act: 5.5182. Min Act: -0.1700
Data Index: 465553 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9244. Min Range: -5.9244
Max Act: 5.5182. Min Act: -0.1700
Data Index: 5500029 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9244. Min Range: -5.9244
Max Act: 5.4869. Min Act: -0.1700
Data Index: 5236937 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9244. Min Range: -5.9244
Max Act: 5.4869. Min Act: -0.1700
Data Index: 2784516 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #19