Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2998 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0186. Min Range: -7.0186
Max Act: 7.0186. Min Act: -0.1700
Data Index: 1975317 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0186. Min Range: -7.0186
Max Act: 6.2998. Min Act: -0.1700
Data Index: 7580684 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0186. Min Range: -7.0186
Max Act: 6.2373. Min Act: -0.1700
Data Index: 7569015 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0186. Min Range: -7.0186
Max Act: 6.2061. Min Act: -0.1700
Data Index: 1012705 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0186. Min Range: -7.0186
Max Act: 6.1748. Min Act: -0.1700
Data Index: 531515 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0186. Min Range: -7.0186
Max Act: 6.1436. Min Act: -0.1700
Data Index: 5778472 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0186. Min Range: -7.0186
Max Act: 6.1123. Min Act: -0.1700
Data Index: 8396937 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0186. Min Range: -7.0186
Max Act: 6.1123. Min Act: -0.1700
Data Index: 7088643 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0186. Min Range: -7.0186
Max Act: 6.0498. Min Act: -0.1700
Data Index: 3217229 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0186. Min Range: -7.0186
Max Act: 6.0186. Min Act: -0.1700
Data Index: 2257680 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0186. Min Range: -7.0186
Max Act: 6.0498. Min Act: -0.1700
Data Index: 4262973 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0186. Min Range: -7.0186
Max Act: 6.0186. Min Act: -0.1700
Data Index: 2922032 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0186. Min Range: -7.0186
Max Act: 6.0186. Min Act: -0.1700
Data Index: 2274866 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0186. Min Range: -7.0186
Max Act: 6.0186. Min Act: -0.1700
Data Index: 7791750 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0186. Min Range: -7.0186
Max Act: 6.0186. Min Act: -0.1700
Data Index: 3510527 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0186. Min Range: -7.0186
Max Act: 6.0186. Min Act: -0.1700
Data Index: 2783721 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0186. Min Range: -7.0186
Max Act: 6.0186. Min Act: -0.1700
Data Index: 3823319 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0186. Min Range: -7.0186
Max Act: 5.9873. Min Act: -0.1700
Data Index: 2871593 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0186. Min Range: -7.0186
Max Act: 5.9873. Min Act: -0.1700
Data Index: 1188113 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0186. Min Range: -7.0186
Max Act: 5.9561. Min Act: -0.1700
Data Index: 4536675 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #19