Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3356 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0817. Min Range: -6.0817
Max Act: 6.0817. Min Act: -0.1700
Data Index: 3955568 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0817. Min Range: -6.0817
Max Act: 5.9254. Min Act: -0.1700
Data Index: 2638928 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0817. Min Range: -6.0817
Max Act: 5.8629. Min Act: -0.1700
Data Index: 8494667 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0817. Min Range: -6.0817
Max Act: 5.8317. Min Act: -0.1700
Data Index: 419444 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0817. Min Range: -6.0817
Max Act: 5.8004. Min Act: -0.1700
Data Index: 4500611 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0817. Min Range: -6.0817
Max Act: 5.7692. Min Act: -0.1700
Data Index: 8457952 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0817. Min Range: -6.0817
Max Act: 5.8004. Min Act: -0.1700
Data Index: 6211973 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0817. Min Range: -6.0817
Max Act: 5.7067. Min Act: -0.1700
Data Index: 6495439 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0817. Min Range: -6.0817
Max Act: 5.7067. Min Act: -0.1700
Data Index: 5495349 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0817. Min Range: -6.0817
Max Act: 5.6754. Min Act: -0.1700
Data Index: 3903321 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0817. Min Range: -6.0817
Max Act: 5.6754. Min Act: -0.1700
Data Index: 3644795 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0817. Min Range: -6.0817
Max Act: 5.6754. Min Act: -0.1700
Data Index: 203760 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0817. Min Range: -6.0817
Max Act: 5.6754. Min Act: -0.1700
Data Index: 4804125 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0817. Min Range: -6.0817
Max Act: 5.6442. Min Act: -0.1700
Data Index: 477520 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0817. Min Range: -6.0817
Max Act: 5.6442. Min Act: -0.1700
Data Index: 7740 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0817. Min Range: -6.0817
Max Act: 5.6442. Min Act: -0.1700
Data Index: 5480465 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0817. Min Range: -6.0817
Max Act: 5.6442. Min Act: -0.1700
Data Index: 199895 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0817. Min Range: -6.0817
Max Act: 5.6129. Min Act: -0.1700
Data Index: 5840760 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0817. Min Range: -6.0817
Max Act: 5.6129. Min Act: -0.1700
Data Index: 3831906 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0817. Min Range: -6.0817
Max Act: 5.5817. Min Act: -0.1700
Data Index: 7328404 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19