Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 389 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5027. Min Range: -5.5027
Max Act: 5.5027. Min Act: -0.1700
Data Index: 5367189 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5027. Min Range: -5.5027
Max Act: 5.4714. Min Act: -0.1700
Data Index: 8096264 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5027. Min Range: -5.5027
Max Act: 5.3777. Min Act: -0.1700
Data Index: 5908491 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5027. Min Range: -5.5027
Max Act: 5.3777. Min Act: -0.1700
Data Index: 4032326 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5027. Min Range: -5.5027
Max Act: 5.3464. Min Act: -0.1700
Data Index: 8215574 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5027. Min Range: -5.5027
Max Act: 5.3152. Min Act: -0.1700
Data Index: 4841468 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5027. Min Range: -5.5027
Max Act: 5.3152. Min Act: -0.1700
Data Index: 5798197 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5027. Min Range: -5.5027
Max Act: 5.3152. Min Act: -0.1700
Data Index: 2281914 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5027. Min Range: -5.5027
Max Act: 5.3152. Min Act: -0.1700
Data Index: 8650719 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5027. Min Range: -5.5027
Max Act: 5.3464. Min Act: -0.1700
Data Index: 3255174 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5027. Min Range: -5.5027
Max Act: 5.3152. Min Act: -0.1700
Data Index: 7614185 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5027. Min Range: -5.5027
Max Act: 5.2839. Min Act: -0.1700
Data Index: 6135802 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5027. Min Range: -5.5027
Max Act: 5.2839. Min Act: -0.1700
Data Index: 895231 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5027. Min Range: -5.5027
Max Act: 5.2839. Min Act: -0.1700
Data Index: 895234 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5027. Min Range: -5.5027
Max Act: 5.2839. Min Act: -0.1700
Data Index: 3320011 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5027. Min Range: -5.5027
Max Act: 5.3152. Min Act: -0.1700
Data Index: 887498 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5027. Min Range: -5.5027
Max Act: 5.2527. Min Act: -0.1700
Data Index: 895222 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5027. Min Range: -5.5027
Max Act: 5.2527. Min Act: -0.1700
Data Index: 6839602 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5027. Min Range: -5.5027
Max Act: 5.2527. Min Act: -0.1700
Data Index: 103064 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5027. Min Range: -5.5027
Max Act: 5.2527. Min Act: -0.1700
Data Index: 5367190 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #19