Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5112 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1836. Min Range: -4.1836
Max Act: 4.1836. Min Act: -0.1700
Data Index: 5131336 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1836. Min Range: -4.1836
Max Act: 4.1524. Min Act: -0.1700
Data Index: 8483109 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1836. Min Range: -4.1836
Max Act: 4.1524. Min Act: -0.1700
Data Index: 7293852 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1836. Min Range: -4.1836
Max Act: 4.0586. Min Act: -0.1700
Data Index: 687551 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1836. Min Range: -4.1836
Max Act: 4.0273. Min Act: -0.1700
Data Index: 3704706 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1836. Min Range: -4.1836
Max Act: 3.9961. Min Act: -0.1700
Data Index: 2339464 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1836. Min Range: -4.1836
Max Act: 3.9648. Min Act: -0.1700
Data Index: 7762130 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1836. Min Range: -4.1836
Max Act: 3.9335. Min Act: -0.1700
Data Index: 3018247 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1836. Min Range: -4.1836
Max Act: 3.9023. Min Act: -0.1700
Data Index: 7487123 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1836. Min Range: -4.1836
Max Act: 3.9023. Min Act: -0.1700
Data Index: 5324823 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1836. Min Range: -4.1836
Max Act: 3.8710. Min Act: -0.1700
Data Index: 8225774 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1836. Min Range: -4.1836
Max Act: 3.8554. Min Act: -0.1700
Data Index: 711149 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1836. Min Range: -4.1836
Max Act: 3.8554. Min Act: -0.1700
Data Index: 324861 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1836. Min Range: -4.1836
Max Act: 3.8554. Min Act: -0.1700
Data Index: 8829269 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1836. Min Range: -4.1836
Max Act: 3.8397. Min Act: -0.1700
Data Index: 8541923 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1836. Min Range: -4.1836
Max Act: 3.8397. Min Act: -0.1700
Data Index: 1760110 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1836. Min Range: -4.1836
Max Act: 3.8241. Min Act: -0.1700
Data Index: 7365805 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1836. Min Range: -4.1836
Max Act: 3.8085. Min Act: -0.1700
Data Index: 7021891 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1836. Min Range: -4.1836
Max Act: 3.8085. Min Act: -0.1700
Data Index: 352340 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1836. Min Range: -4.1836
Max Act: 3.7772. Min Act: -0.1700
Data Index: 5150495 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #19