Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4251 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3911. Min Range: -4.3911
Max Act: 4.3911. Min Act: -0.1700
Data Index: 4707129 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3911. Min Range: -4.3911
Max Act: 4.1099. Min Act: -0.1700
Data Index: 4895027 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3911. Min Range: -4.3911
Max Act: 4.1099. Min Act: -0.1700
Data Index: 7026371 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3911. Min Range: -4.3911
Max Act: 3.9848. Min Act: -0.1700
Data Index: 4873939 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3911. Min Range: -4.3911
Max Act: 3.9848. Min Act: -0.1700
Data Index: 3846011 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3911. Min Range: -4.3911
Max Act: 3.9848. Min Act: -0.1700
Data Index: 79118 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3911. Min Range: -4.3911
Max Act: 3.9848. Min Act: -0.1700
Data Index: 6559077 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3911. Min Range: -4.3911
Max Act: 3.9848. Min Act: -0.1700
Data Index: 2696162 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3911. Min Range: -4.3911
Max Act: 3.9848. Min Act: -0.1700
Data Index: 4438742 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3911. Min Range: -4.3911
Max Act: 3.9223. Min Act: -0.1700
Data Index: 389900 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3911. Min Range: -4.3911
Max Act: 3.9536. Min Act: -0.1700
Data Index: 5739778 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3911. Min Range: -4.3911
Max Act: 3.9223. Min Act: -0.1700
Data Index: 1112281 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3911. Min Range: -4.3911
Max Act: 3.9223. Min Act: -0.1700
Data Index: 8216527 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3911. Min Range: -4.3911
Max Act: 3.9223. Min Act: -0.1700
Data Index: 6086112 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3911. Min Range: -4.3911
Max Act: 3.8910. Min Act: -0.1700
Data Index: 1973954 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3911. Min Range: -4.3911
Max Act: 3.8910. Min Act: -0.1700
Data Index: 7804880 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3911. Min Range: -4.3911
Max Act: 3.8598. Min Act: -0.1700
Data Index: 4945049 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3911. Min Range: -4.3911
Max Act: 3.8285. Min Act: -0.1700
Data Index: 541756 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3911. Min Range: -4.3911
Max Act: 3.8285. Min Act: -0.1700
Data Index: 6180605 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3911. Min Range: -4.3911
Max Act: 3.8285. Min Act: -0.1700
Data Index: 7119984 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #19