Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1824 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6027. Min Range: -5.6027
Max Act: 5.6027. Min Act: -0.1700
Data Index: 1111603 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6027. Min Range: -5.6027
Max Act: 5.5089. Min Act: -0.1700
Data Index: 3221823 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6027. Min Range: -5.6027
Max Act: 5.5089. Min Act: -0.1700
Data Index: 8406378 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6027. Min Range: -5.6027
Max Act: 5.4777. Min Act: -0.1700
Data Index: 3159989 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6027. Min Range: -5.6027
Max Act: 5.4464. Min Act: -0.1700
Data Index: 1550327 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6027. Min Range: -5.6027
Max Act: 5.4464. Min Act: -0.1700
Data Index: 285927 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6027. Min Range: -5.6027
Max Act: 5.4464. Min Act: -0.1700
Data Index: 4450159 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6027. Min Range: -5.6027
Max Act: 5.4152. Min Act: -0.1700
Data Index: 8516844 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6027. Min Range: -5.6027
Max Act: 5.4464. Min Act: -0.1700
Data Index: 8071075 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6027. Min Range: -5.6027
Max Act: 5.4152. Min Act: -0.1700
Data Index: 7957267 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6027. Min Range: -5.6027
Max Act: 5.4464. Min Act: -0.1700
Data Index: 2016117 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6027. Min Range: -5.6027
Max Act: 5.4464. Min Act: -0.1700
Data Index: 3571370 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6027. Min Range: -5.6027
Max Act: 5.4152. Min Act: -0.1700
Data Index: 2005980 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6027. Min Range: -5.6027
Max Act: 5.4464. Min Act: -0.1700
Data Index: 8560518 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6027. Min Range: -5.6027
Max Act: 5.4777. Min Act: -0.1700
Data Index: 4466069 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6027. Min Range: -5.6027
Max Act: 5.4464. Min Act: -0.1700
Data Index: 340188 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6027. Min Range: -5.6027
Max Act: 5.4152. Min Act: -0.1700
Data Index: 3754115 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6027. Min Range: -5.6027
Max Act: 5.4152. Min Act: -0.1700
Data Index: 7753437 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6027. Min Range: -5.6027
Max Act: 5.4152. Min Act: -0.1700
Data Index: 5320093 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6027. Min Range: -5.6027
Max Act: 5.4152. Min Act: -0.1700
Data Index: 1257032 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19