Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4415 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6777. Min Range: -7.6777
Max Act: 7.6777. Min Act: -0.1700
Data Index: 1688070 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6777. Min Range: -7.6777
Max Act: 7.5840. Min Act: -0.1700
Data Index: 4182333 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6777. Min Range: -7.6777
Max Act: 7.4277. Min Act: -0.1700
Data Index: 5658896 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6777. Min Range: -7.6777
Max Act: 7.4277. Min Act: -0.1700
Data Index: 6900686 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6777. Min Range: -7.6777
Max Act: 7.3340. Min Act: -0.1700
Data Index: 5206686 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6777. Min Range: -7.6777
Max Act: 7.2715. Min Act: -0.1700
Data Index: 1041489 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6777. Min Range: -7.6777
Max Act: 7.2402. Min Act: -0.1700
Data Index: 8085791 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6777. Min Range: -7.6777
Max Act: 7.2402. Min Act: -0.1700
Data Index: 7658490 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6777. Min Range: -7.6777
Max Act: 7.2090. Min Act: -0.1700
Data Index: 6462118 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6777. Min Range: -7.6777
Max Act: 7.2090. Min Act: -0.1700
Data Index: 5696885 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6777. Min Range: -7.6777
Max Act: 7.1777. Min Act: -0.1700
Data Index: 6912149 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6777. Min Range: -7.6777
Max Act: 7.1777. Min Act: -0.1700
Data Index: 1438810 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6777. Min Range: -7.6777
Max Act: 7.1777. Min Act: -0.1700
Data Index: 1839924 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6777. Min Range: -7.6777
Max Act: 7.1777. Min Act: -0.1700
Data Index: 7559988 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6777. Min Range: -7.6777
Max Act: 7.1777. Min Act: -0.1700
Data Index: 2563848 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6777. Min Range: -7.6777
Max Act: 7.1465. Min Act: -0.1700
Data Index: 819565 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6777. Min Range: -7.6777
Max Act: 7.1152. Min Act: -0.1700
Data Index: 2072290 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6777. Min Range: -7.6777
Max Act: 7.0840. Min Act: -0.1700
Data Index: 8415748 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6777. Min Range: -7.6777
Max Act: 7.0840. Min Act: -0.1700
Data Index: 7687271 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6777. Min Range: -7.6777
Max Act: 7.0840. Min Act: -0.1700
Data Index: 3197638 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19