Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3898 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4753. Min Range: -5.4753
Max Act: 5.4753. Min Act: -0.1700
Data Index: 7994884 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4753. Min Range: -5.4753
Max Act: 5.3190. Min Act: -0.1700
Data Index: 7754505 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4753. Min Range: -5.4753
Max Act: 5.2878. Min Act: -0.1700
Data Index: 3277300 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4753. Min Range: -5.4753
Max Act: 5.2565. Min Act: -0.1700
Data Index: 4557456 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4753. Min Range: -5.4753
Max Act: 5.1940. Min Act: -0.1700
Data Index: 7293920 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4753. Min Range: -5.4753
Max Act: 5.1315. Min Act: -0.1700
Data Index: 2455896 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4753. Min Range: -5.4753
Max Act: 5.1003. Min Act: -0.1700
Data Index: 3539231 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4753. Min Range: -5.4753
Max Act: 5.1003. Min Act: -0.1700
Data Index: 8231211 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4753. Min Range: -5.4753
Max Act: 5.1003. Min Act: -0.1700
Data Index: 7088733 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4753. Min Range: -5.4753
Max Act: 5.1003. Min Act: -0.1700
Data Index: 329038 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4753. Min Range: -5.4753
Max Act: 5.0690. Min Act: -0.1700
Data Index: 7647892 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4753. Min Range: -5.4753
Max Act: 5.0690. Min Act: -0.1700
Data Index: 4362795 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4753. Min Range: -5.4753
Max Act: 5.0690. Min Act: -0.1700
Data Index: 4977639 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4753. Min Range: -5.4753
Max Act: 5.0378. Min Act: -0.1700
Data Index: 8467651 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4753. Min Range: -5.4753
Max Act: 5.0690. Min Act: -0.1700
Data Index: 3625682 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4753. Min Range: -5.4753
Max Act: 5.0378. Min Act: -0.1700
Data Index: 6300853 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4753. Min Range: -5.4753
Max Act: 5.0378. Min Act: -0.1700
Data Index: 797675 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4753. Min Range: -5.4753
Max Act: 5.0690. Min Act: -0.1700
Data Index: 2473848 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4753. Min Range: -5.4753
Max Act: 5.0065. Min Act: -0.1700
Data Index: 1636707 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4753. Min Range: -5.4753
Max Act: 5.0065. Min Act: -0.1700
Data Index: 1937259 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #19