Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4114 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7200. Min Range: -5.7200
Max Act: 5.7200. Min Act: -0.1700
Data Index: 5131171 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7200. Min Range: -5.7200
Max Act: 5.6887. Min Act: -0.1700
Data Index: 3344519 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7200. Min Range: -5.7200
Max Act: 5.6575. Min Act: -0.1700
Data Index: 7918954 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7200. Min Range: -5.7200
Max Act: 5.6575. Min Act: -0.1700
Data Index: 7725750 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7200. Min Range: -5.7200
Max Act: 5.5950. Min Act: -0.1700
Data Index: 736253 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7200. Min Range: -5.7200
Max Act: 5.5950. Min Act: -0.1700
Data Index: 3087166 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7200. Min Range: -5.7200
Max Act: 5.5950. Min Act: -0.1700
Data Index: 1901321 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7200. Min Range: -5.7200
Max Act: 5.5637. Min Act: -0.1700
Data Index: 7725752 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7200. Min Range: -5.7200
Max Act: 5.5012. Min Act: -0.1700
Data Index: 7032341 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7200. Min Range: -5.7200
Max Act: 5.4700. Min Act: -0.1700
Data Index: 4345212 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7200. Min Range: -5.7200
Max Act: 5.4700. Min Act: -0.1700
Data Index: 3677007 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7200. Min Range: -5.7200
Max Act: 5.4700. Min Act: -0.1700
Data Index: 4464204 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7200. Min Range: -5.7200
Max Act: 5.4387. Min Act: -0.1700
Data Index: 7488025 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7200. Min Range: -5.7200
Max Act: 5.4387. Min Act: -0.1700
Data Index: 7765172 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7200. Min Range: -5.7200
Max Act: 5.4075. Min Act: -0.1700
Data Index: 6717253 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7200. Min Range: -5.7200
Max Act: 5.4387. Min Act: -0.1700
Data Index: 1988239 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7200. Min Range: -5.7200
Max Act: 5.4075. Min Act: -0.1700
Data Index: 4247251 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7200. Min Range: -5.7200
Max Act: 5.4075. Min Act: -0.1700
Data Index: 3865984 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7200. Min Range: -5.7200
Max Act: 5.3762. Min Act: -0.1700
Data Index: 458386 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7200. Min Range: -5.7200
Max Act: 5.3762. Min Act: -0.1700
Data Index: 1730253 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #19