Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3994 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7922. Min Range: -6.7922
Max Act: 6.7922. Min Act: -0.1700
Data Index: 5826561 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7922. Min Range: -6.7922
Max Act: 6.7922. Min Act: -0.1700
Data Index: 6372543 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7922. Min Range: -6.7922
Max Act: 6.6984. Min Act: -0.1700
Data Index: 3305224 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7922. Min Range: -6.7922
Max Act: 6.6672. Min Act: -0.1700
Data Index: 5185966 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7922. Min Range: -6.7922
Max Act: 6.6672. Min Act: -0.1700
Data Index: 7402988 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7922. Min Range: -6.7922
Max Act: 6.5734. Min Act: -0.1700
Data Index: 7873069 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7922. Min Range: -6.7922
Max Act: 6.6047. Min Act: -0.1700
Data Index: 2968300 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7922. Min Range: -6.7922
Max Act: 6.5734. Min Act: -0.1700
Data Index: 1508723 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7922. Min Range: -6.7922
Max Act: 6.6047. Min Act: -0.1700
Data Index: 6153017 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7922. Min Range: -6.7922
Max Act: 6.5422. Min Act: -0.1700
Data Index: 4855987 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7922. Min Range: -6.7922
Max Act: 6.5422. Min Act: -0.1700
Data Index: 1282989 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7922. Min Range: -6.7922
Max Act: 6.5109. Min Act: -0.1700
Data Index: 1972833 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7922. Min Range: -6.7922
Max Act: 6.4797. Min Act: -0.1700
Data Index: 5600704 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7922. Min Range: -6.7922
Max Act: 6.4172. Min Act: -0.1700
Data Index: 818649 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7922. Min Range: -6.7922
Max Act: 6.3859. Min Act: -0.1700
Data Index: 136345 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7922. Min Range: -6.7922
Max Act: 6.3859. Min Act: -0.1700
Data Index: 4432527 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7922. Min Range: -6.7922
Max Act: 6.3859. Min Act: -0.1700
Data Index: 2295404 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7922. Min Range: -6.7922
Max Act: 6.3547. Min Act: -0.1700
Data Index: 5700850 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7922. Min Range: -6.7922
Max Act: 6.3234. Min Act: -0.1700
Data Index: 3902502 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7922. Min Range: -6.7922
Max Act: 6.2922. Min Act: -0.1700
Data Index: 1018131 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19