Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2067 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7083. Min Range: -3.7083
Max Act: 3.7083. Min Act: -0.1700
Data Index: 8476348 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7083. Min Range: -3.7083
Max Act: 3.7083. Min Act: -0.1700
Data Index: 4572304 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7083. Min Range: -3.7083
Max Act: 3.7083. Min Act: -0.1700
Data Index: 8470481 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7083. Min Range: -3.7083
Max Act: 3.7083. Min Act: -0.1700
Data Index: 872689 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7083. Min Range: -3.7083
Max Act: 3.7083. Min Act: -0.1700
Data Index: 3687435 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7083. Min Range: -3.7083
Max Act: 3.7083. Min Act: -0.1700
Data Index: 1131995 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7083. Min Range: -3.7083
Max Act: 3.7083. Min Act: -0.1700
Data Index: 7331330 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7083. Min Range: -3.7083
Max Act: 3.7083. Min Act: -0.1700
Data Index: 6011545 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7083. Min Range: -3.7083
Max Act: 3.6770. Min Act: -0.1700
Data Index: 6381115 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7083. Min Range: -3.7083
Max Act: 3.6926. Min Act: -0.1700
Data Index: 1525617 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7083. Min Range: -3.7083
Max Act: 3.6613. Min Act: -0.1700
Data Index: 3787468 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7083. Min Range: -3.7083
Max Act: 3.6613. Min Act: -0.1700
Data Index: 1019134 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7083. Min Range: -3.7083
Max Act: 3.6300. Min Act: -0.1700
Data Index: 1353888 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7083. Min Range: -3.7083
Max Act: 3.6144. Min Act: -0.1700
Data Index: 2831250 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7083. Min Range: -3.7083
Max Act: 3.6144. Min Act: -0.1700
Data Index: 3164981 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7083. Min Range: -3.7083
Max Act: 3.6457. Min Act: -0.1700
Data Index: 2730299 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7083. Min Range: -3.7083
Max Act: 3.6144. Min Act: -0.1700
Data Index: 7056093 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7083. Min Range: -3.7083
Max Act: 3.6144. Min Act: -0.1700
Data Index: 7230796 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7083. Min Range: -3.7083
Max Act: 3.5987. Min Act: -0.1700
Data Index: 5531729 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7083. Min Range: -3.7083
Max Act: 3.5831. Min Act: -0.1700
Data Index: 4142743 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #19