Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2108 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7914. Min Range: -5.7914
Max Act: 5.7914. Min Act: -0.1700
Data Index: 1070160 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7914. Min Range: -5.7914
Max Act: 5.7289. Min Act: -0.1700
Data Index: 8625238 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7914. Min Range: -5.7914
Max Act: 5.6977. Min Act: -0.1700
Data Index: 5844488 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7914. Min Range: -5.7914
Max Act: 5.6977. Min Act: -0.1700
Data Index: 1843691 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7914. Min Range: -5.7914
Max Act: 5.6977. Min Act: -0.1700
Data Index: 8220392 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7914. Min Range: -5.7914
Max Act: 5.6664. Min Act: -0.1700
Data Index: 3475205 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7914. Min Range: -5.7914
Max Act: 5.6664. Min Act: -0.1700
Data Index: 3489061 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7914. Min Range: -5.7914
Max Act: 5.6352. Min Act: -0.1700
Data Index: 958062 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7914. Min Range: -5.7914
Max Act: 5.5414. Min Act: -0.1700
Data Index: 3503659 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7914. Min Range: -5.7914
Max Act: 5.5727. Min Act: -0.1700
Data Index: 3814914 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7914. Min Range: -5.7914
Max Act: 5.5727. Min Act: -0.1700
Data Index: 2193704 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7914. Min Range: -5.7914
Max Act: 5.5727. Min Act: -0.1700
Data Index: 7692967 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7914. Min Range: -5.7914
Max Act: 5.5414. Min Act: -0.1700
Data Index: 1514164 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7914. Min Range: -5.7914
Max Act: 5.5727. Min Act: -0.1700
Data Index: 1320410 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7914. Min Range: -5.7914
Max Act: 5.5414. Min Act: -0.1700
Data Index: 7294973 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7914. Min Range: -5.7914
Max Act: 5.5102. Min Act: -0.1700
Data Index: 5334017 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7914. Min Range: -5.7914
Max Act: 5.5102. Min Act: -0.1700
Data Index: 4342438 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7914. Min Range: -5.7914
Max Act: 5.5102. Min Act: -0.1700
Data Index: 7179917 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7914. Min Range: -5.7914
Max Act: 5.5414. Min Act: -0.1700
Data Index: 5124663 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7914. Min Range: -5.7914
Max Act: 5.5102. Min Act: -0.1700
Data Index: 6050807 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19