Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3017 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8829. Min Range: -5.8829
Max Act: 5.8829. Min Act: -0.1700
Data Index: 7751632 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8829. Min Range: -5.8829
Max Act: 5.7579. Min Act: -0.1700
Data Index: 183310 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8829. Min Range: -5.8829
Max Act: 5.7579. Min Act: -0.1700
Data Index: 1552517 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8829. Min Range: -5.8829
Max Act: 5.7267. Min Act: -0.1700
Data Index: 5833497 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8829. Min Range: -5.8829
Max Act: 5.6642. Min Act: -0.1700
Data Index: 5205373 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8829. Min Range: -5.8829
Max Act: 5.6954. Min Act: -0.1700
Data Index: 2094504 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8829. Min Range: -5.8829
Max Act: 5.6329. Min Act: -0.1700
Data Index: 8806894 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8829. Min Range: -5.8829
Max Act: 5.4767. Min Act: -0.1700
Data Index: 6743362 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8829. Min Range: -5.8829
Max Act: 5.4767. Min Act: -0.1700
Data Index: 4826663 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8829. Min Range: -5.8829
Max Act: 5.4767. Min Act: -0.1700
Data Index: 2174956 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8829. Min Range: -5.8829
Max Act: 5.3829. Min Act: -0.1700
Data Index: 4487964 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8829. Min Range: -5.8829
Max Act: 5.3829. Min Act: -0.1700
Data Index: 2973950 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8829. Min Range: -5.8829
Max Act: 5.3517. Min Act: -0.1700
Data Index: 3690731 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8829. Min Range: -5.8829
Max Act: 5.3517. Min Act: -0.1700
Data Index: 6461912 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8829. Min Range: -5.8829
Max Act: 5.3204. Min Act: -0.1700
Data Index: 1906358 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8829. Min Range: -5.8829
Max Act: 5.2892. Min Act: -0.1700
Data Index: 5680970 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8829. Min Range: -5.8829
Max Act: 5.2892. Min Act: -0.1700
Data Index: 111993 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8829. Min Range: -5.8829
Max Act: 5.2892. Min Act: -0.1700
Data Index: 5947924 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8829. Min Range: -5.8829
Max Act: 5.2892. Min Act: -0.1700
Data Index: 7000587 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8829. Min Range: -5.8829
Max Act: 5.2579. Min Act: -0.1700
Data Index: 5284227 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #19