Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1765 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9285. Min Range: -4.9285
Max Act: 4.9285. Min Act: -0.1700
Data Index: 1253518 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9285. Min Range: -4.9285
Max Act: 4.8973. Min Act: -0.1700
Data Index: 2941150 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9285. Min Range: -4.9285
Max Act: 4.6473. Min Act: -0.1700
Data Index: 3008388 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9285. Min Range: -4.9285
Max Act: 4.5848. Min Act: -0.1700
Data Index: 8049307 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9285. Min Range: -4.9285
Max Act: 4.5535. Min Act: -0.1700
Data Index: 2718597 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9285. Min Range: -4.9285
Max Act: 4.5535. Min Act: -0.1700
Data Index: 3309969 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9285. Min Range: -4.9285
Max Act: 4.5535. Min Act: -0.1700
Data Index: 5858045 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9285. Min Range: -4.9285
Max Act: 4.5223. Min Act: -0.1700
Data Index: 1159114 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9285. Min Range: -4.9285
Max Act: 4.4910. Min Act: -0.1700
Data Index: 1210950 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9285. Min Range: -4.9285
Max Act: 4.5223. Min Act: -0.1700
Data Index: 2263208 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9285. Min Range: -4.9285
Max Act: 4.5223. Min Act: -0.1700
Data Index: 5587226 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9285. Min Range: -4.9285
Max Act: 4.4598. Min Act: -0.1700
Data Index: 1621107 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9285. Min Range: -4.9285
Max Act: 4.4910. Min Act: -0.1700
Data Index: 4775014 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9285. Min Range: -4.9285
Max Act: 4.4598. Min Act: -0.1700
Data Index: 7809647 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9285. Min Range: -4.9285
Max Act: 4.4598. Min Act: -0.1700
Data Index: 6044376 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9285. Min Range: -4.9285
Max Act: 4.4598. Min Act: -0.1700
Data Index: 4375941 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9285. Min Range: -4.9285
Max Act: 4.4285. Min Act: -0.1700
Data Index: 3120647 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9285. Min Range: -4.9285
Max Act: 4.4598. Min Act: -0.1700
Data Index: 5145554 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9285. Min Range: -4.9285
Max Act: 4.4285. Min Act: -0.1700
Data Index: 7589838 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9285. Min Range: -4.9285
Max Act: 4.4598. Min Act: -0.1700
Data Index: 4303749 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #19