Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5721 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5767. Min Range: -4.5767
Max Act: 4.5767. Min Act: -0.1700
Data Index: 3638945 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5767. Min Range: -4.5767
Max Act: 4.5454. Min Act: -0.1700
Data Index: 1679079 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5767. Min Range: -4.5767
Max Act: 4.5454. Min Act: -0.1700
Data Index: 7327283 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5767. Min Range: -4.5767
Max Act: 4.4829. Min Act: -0.1700
Data Index: 2117166 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5767. Min Range: -4.5767
Max Act: 4.4829. Min Act: -0.1700
Data Index: 8111906 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5767. Min Range: -4.5767
Max Act: 4.4829. Min Act: -0.1700
Data Index: 7440271 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5767. Min Range: -4.5767
Max Act: 4.4517. Min Act: -0.1700
Data Index: 4233497 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5767. Min Range: -4.5767
Max Act: 4.4204. Min Act: -0.1700
Data Index: 6199687 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5767. Min Range: -4.5767
Max Act: 4.3892. Min Act: -0.1700
Data Index: 7286903 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5767. Min Range: -4.5767
Max Act: 4.3579. Min Act: -0.1700
Data Index: 180295 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5767. Min Range: -4.5767
Max Act: 4.3892. Min Act: -0.1700
Data Index: 5623169 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5767. Min Range: -4.5767
Max Act: 4.3579. Min Act: -0.1700
Data Index: 3790656 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5767. Min Range: -4.5767
Max Act: 4.3579. Min Act: -0.1700
Data Index: 562393 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5767. Min Range: -4.5767
Max Act: 4.3267. Min Act: -0.1700
Data Index: 6260160 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5767. Min Range: -4.5767
Max Act: 4.3579. Min Act: -0.1700
Data Index: 1395708 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5767. Min Range: -4.5767
Max Act: 4.3267. Min Act: -0.1700
Data Index: 381836 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5767. Min Range: -4.5767
Max Act: 4.2954. Min Act: -0.1700
Data Index: 3991351 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5767. Min Range: -4.5767
Max Act: 4.3267. Min Act: -0.1700
Data Index: 6919253 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5767. Min Range: -4.5767
Max Act: 4.2954. Min Act: -0.1700
Data Index: 5036205 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5767. Min Range: -4.5767
Max Act: 4.3267. Min Act: -0.1700
Data Index: 675385 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19