Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3437 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3953. Min Range: -4.3953
Max Act: 4.3953. Min Act: -0.1700
Data Index: 4261436 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3953. Min Range: -4.3953
Max Act: 4.3641. Min Act: -0.1700
Data Index: 2186274 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3953. Min Range: -4.3953
Max Act: 4.3328. Min Act: -0.1700
Data Index: 5058127 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3953. Min Range: -4.3953
Max Act: 4.3328. Min Act: -0.1700
Data Index: 6934010 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3953. Min Range: -4.3953
Max Act: 4.2703. Min Act: -0.1700
Data Index: 3438783 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3953. Min Range: -4.3953
Max Act: 4.2703. Min Act: -0.1700
Data Index: 4836685 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3953. Min Range: -4.3953
Max Act: 4.2390. Min Act: -0.1700
Data Index: 3124758 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3953. Min Range: -4.3953
Max Act: 4.1765. Min Act: -0.1700
Data Index: 6345925 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3953. Min Range: -4.3953
Max Act: 4.2390. Min Act: -0.1700
Data Index: 603145 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3953. Min Range: -4.3953
Max Act: 4.2390. Min Act: -0.1700
Data Index: 6718769 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3953. Min Range: -4.3953
Max Act: 4.1765. Min Act: -0.1700
Data Index: 3891370 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3953. Min Range: -4.3953
Max Act: 4.2078. Min Act: -0.1700
Data Index: 1450327 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3953. Min Range: -4.3953
Max Act: 4.1765. Min Act: -0.1700
Data Index: 1931381 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3953. Min Range: -4.3953
Max Act: 4.2078. Min Act: -0.1700
Data Index: 2986411 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3953. Min Range: -4.3953
Max Act: 4.1453. Min Act: -0.1700
Data Index: 6934009 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3953. Min Range: -4.3953
Max Act: 4.1453. Min Act: -0.1700
Data Index: 8175727 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3953. Min Range: -4.3953
Max Act: 4.1140. Min Act: -0.1700
Data Index: 2900693 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3953. Min Range: -4.3953
Max Act: 4.1453. Min Act: -0.1700
Data Index: 3655728 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3953. Min Range: -4.3953
Max Act: 4.1453. Min Act: -0.1700
Data Index: 639226 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3953. Min Range: -4.3953
Max Act: 4.1140. Min Act: -0.1700
Data Index: 6046847 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19