Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1235 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8890. Min Range: -7.8890
Max Act: 7.8890. Min Act: -0.1700
Data Index: 1726548 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8890. Min Range: -7.8890
Max Act: 7.4827. Min Act: -0.1700
Data Index: 1565626 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8890. Min Range: -7.8890
Max Act: 7.3890. Min Act: -0.1700
Data Index: 3735688 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8890. Min Range: -7.8890
Max Act: 7.4202. Min Act: -0.1700
Data Index: 4646698 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8890. Min Range: -7.8890
Max Act: 7.3890. Min Act: -0.1700
Data Index: 3640865 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8890. Min Range: -7.8890
Max Act: 7.3890. Min Act: -0.1700
Data Index: 2067860 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8890. Min Range: -7.8890
Max Act: 7.3577. Min Act: -0.1700
Data Index: 201295 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8890. Min Range: -7.8890
Max Act: 7.3265. Min Act: -0.1700
Data Index: 3735689 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8890. Min Range: -7.8890
Max Act: 7.2952. Min Act: -0.1700
Data Index: 3977780 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8890. Min Range: -7.8890
Max Act: 7.2952. Min Act: -0.1700
Data Index: 2352771 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8890. Min Range: -7.8890
Max Act: 7.2952. Min Act: -0.1700
Data Index: 2770131 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8890. Min Range: -7.8890
Max Act: 7.3265. Min Act: -0.1700
Data Index: 201296 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8890. Min Range: -7.8890
Max Act: 7.2327. Min Act: -0.1700
Data Index: 3143904 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8890. Min Range: -7.8890
Max Act: 7.1702. Min Act: -0.1700
Data Index: 4571479 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8890. Min Range: -7.8890
Max Act: 7.1390. Min Act: -0.1700
Data Index: 4242436 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8890. Min Range: -7.8890
Max Act: 7.1390. Min Act: -0.1700
Data Index: 241622 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8890. Min Range: -7.8890
Max Act: 7.1077. Min Act: -0.1700
Data Index: 701871 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8890. Min Range: -7.8890
Max Act: 7.1077. Min Act: -0.1700
Data Index: 4844976 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8890. Min Range: -7.8890
Max Act: 7.1077. Min Act: -0.1700
Data Index: 4951937 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8890. Min Range: -7.8890
Max Act: 7.0452. Min Act: -0.1700
Data Index: 5542771 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19