Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2931 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2039. Min Range: -4.2039
Max Act: 4.2039. Min Act: -0.1700
Data Index: 5199151 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2039. Min Range: -4.2039
Max Act: 4.2039. Min Act: -0.1700
Data Index: 5187258 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2039. Min Range: -4.2039
Max Act: 4.1727. Min Act: -0.1700
Data Index: 8226438 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2039. Min Range: -4.2039
Max Act: 4.1102. Min Act: -0.1700
Data Index: 6782252 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2039. Min Range: -4.2039
Max Act: 4.1102. Min Act: -0.1700
Data Index: 1173374 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2039. Min Range: -4.2039
Max Act: 4.0789. Min Act: -0.1700
Data Index: 1669200 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2039. Min Range: -4.2039
Max Act: 4.0789. Min Act: -0.1700
Data Index: 2074437 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2039. Min Range: -4.2039
Max Act: 4.0789. Min Act: -0.1700
Data Index: 3244972 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2039. Min Range: -4.2039
Max Act: 4.1102. Min Act: -0.1700
Data Index: 2216346 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2039. Min Range: -4.2039
Max Act: 4.0789. Min Act: -0.1700
Data Index: 884012 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2039. Min Range: -4.2039
Max Act: 4.0789. Min Act: -0.1700
Data Index: 6595491 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2039. Min Range: -4.2039
Max Act: 4.0477. Min Act: -0.1700
Data Index: 5607371 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2039. Min Range: -4.2039
Max Act: 4.0477. Min Act: -0.1700
Data Index: 1638698 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2039. Min Range: -4.2039
Max Act: 4.0477. Min Act: -0.1700
Data Index: 3344357 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2039. Min Range: -4.2039
Max Act: 4.0164. Min Act: -0.1700
Data Index: 5418192 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2039. Min Range: -4.2039
Max Act: 4.0789. Min Act: -0.1700
Data Index: 157950 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2039. Min Range: -4.2039
Max Act: 4.0164. Min Act: -0.1700
Data Index: 2793267 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2039. Min Range: -4.2039
Max Act: 4.0164. Min Act: -0.1700
Data Index: 2845365 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2039. Min Range: -4.2039
Max Act: 4.0164. Min Act: -0.1700
Data Index: 2507284 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2039. Min Range: -4.2039
Max Act: 4.0477. Min Act: -0.1700
Data Index: 3234043 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #19