Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3669 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5640. Min Range: -3.5640
Max Act: 3.5640. Min Act: -0.1700
Data Index: 7303682 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5640. Min Range: -3.5640
Max Act: 3.4857. Min Act: -0.1700
Data Index: 826247 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5640. Min Range: -3.5640
Max Act: 3.3760. Min Act: -0.1700
Data Index: 6353633 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5640. Min Range: -3.5640
Max Act: 3.2661. Min Act: -0.1700
Data Index: 1078472 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5640. Min Range: -3.5640
Max Act: 3.2504. Min Act: -0.1700
Data Index: 1503205 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5640. Min Range: -3.5640
Max Act: 3.1718. Min Act: -0.1700
Data Index: 6807241 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5640. Min Range: -3.5640
Max Act: 3.1718. Min Act: -0.1700
Data Index: 6388002 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5640. Min Range: -3.5640
Max Act: 3.1560. Min Act: -0.1700
Data Index: 7532186 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5640. Min Range: -3.5640
Max Act: 3.1718. Min Act: -0.1700
Data Index: 1262703 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5640. Min Range: -3.5640
Max Act: 3.1403. Min Act: -0.1700
Data Index: 8691696 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5640. Min Range: -3.5640
Max Act: 3.1403. Min Act: -0.1700
Data Index: 4398187 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5640. Min Range: -3.5640
Max Act: 3.1245. Min Act: -0.1700
Data Index: 5963388 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5640. Min Range: -3.5640
Max Act: 3.1088. Min Act: -0.1700
Data Index: 36086 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5640. Min Range: -3.5640
Max Act: 3.0930. Min Act: -0.1700
Data Index: 443829 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5640. Min Range: -3.5640
Max Act: 3.0773. Min Act: -0.1700
Data Index: 7419696 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5640. Min Range: -3.5640
Max Act: 3.0930. Min Act: -0.1700
Data Index: 5574108 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5640. Min Range: -3.5640
Max Act: 3.0457. Min Act: -0.1700
Data Index: 5180154 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5640. Min Range: -3.5640
Max Act: 3.0773. Min Act: -0.1700
Data Index: 4552566 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5640. Min Range: -3.5640
Max Act: 3.0615. Min Act: -0.1700
Data Index: 5437295 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5640. Min Range: -3.5640
Max Act: 3.0615. Min Act: -0.1700
Data Index: 6920276 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #19