Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1930 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.8711. Min Range: -7.8711
Max Act: 7.8711. Min Act: -0.1700
Data Index: 7359432 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8711. Min Range: -7.8711
Max Act: 7.4648. Min Act: -0.1700
Data Index: 4391515 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8711. Min Range: -7.8711
Max Act: 7.2773. Min Act: -0.1700
Data Index: 7871391 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8711. Min Range: -7.8711
Max Act: 7.2461. Min Act: -0.1700
Data Index: 2967226 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8711. Min Range: -7.8711
Max Act: 7.2461. Min Act: -0.1700
Data Index: 430145 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8711. Min Range: -7.8711
Max Act: 7.2148. Min Act: -0.1700
Data Index: 4617752 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8711. Min Range: -7.8711
Max Act: 7.2148. Min Act: -0.1700
Data Index: 2311608 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8711. Min Range: -7.8711
Max Act: 7.1836. Min Act: -0.1700
Data Index: 7568114 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8711. Min Range: -7.8711
Max Act: 7.2148. Min Act: -0.1700
Data Index: 5435559 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8711. Min Range: -7.8711
Max Act: 7.1836. Min Act: -0.1700
Data Index: 6481993 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8711. Min Range: -7.8711
Max Act: 7.1836. Min Act: -0.1700
Data Index: 5085945 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8711. Min Range: -7.8711
Max Act: 7.1523. Min Act: -0.1700
Data Index: 5612243 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8711. Min Range: -7.8711
Max Act: 7.1836. Min Act: -0.1700
Data Index: 7405885 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8711. Min Range: -7.8711
Max Act: 7.1523. Min Act: -0.1700
Data Index: 7813541 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8711. Min Range: -7.8711
Max Act: 7.1836. Min Act: -0.1700
Data Index: 4852434 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8711. Min Range: -7.8711
Max Act: 7.1211. Min Act: -0.1700
Data Index: 656966 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8711. Min Range: -7.8711
Max Act: 7.1211. Min Act: -0.1700
Data Index: 5317892 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8711. Min Range: -7.8711
Max Act: 7.1523. Min Act: -0.1700
Data Index: 6147266 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8711. Min Range: -7.8711
Max Act: 7.1211. Min Act: -0.1700
Data Index: 8604288 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8711. Min Range: -7.8711
Max Act: 7.0898. Min Act: -0.1700
Data Index: 6827705 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19