Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1062 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3628. Min Range: -6.3628
Max Act: 6.3628. Min Act: -0.1700
Data Index: 3436704 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3628. Min Range: -6.3628
Max Act: 6.2378. Min Act: -0.1700
Data Index: 2344278 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3628. Min Range: -6.3628
Max Act: 6.1753. Min Act: -0.1700
Data Index: 4346845 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3628. Min Range: -6.3628
Max Act: 5.9253. Min Act: -0.1700
Data Index: 5642503 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3628. Min Range: -6.3628
Max Act: 5.9253. Min Act: -0.1700
Data Index: 1541557 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3628. Min Range: -6.3628
Max Act: 5.8940. Min Act: -0.1700
Data Index: 2893060 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3628. Min Range: -6.3628
Max Act: 5.8940. Min Act: -0.1700
Data Index: 8323974 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3628. Min Range: -6.3628
Max Act: 5.8628. Min Act: -0.1700
Data Index: 5450313 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3628. Min Range: -6.3628
Max Act: 5.8628. Min Act: -0.1700
Data Index: 6640718 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3628. Min Range: -6.3628
Max Act: 5.8315. Min Act: -0.1700
Data Index: 5525840 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3628. Min Range: -6.3628
Max Act: 5.8315. Min Act: -0.1700
Data Index: 6769875 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3628. Min Range: -6.3628
Max Act: 5.8315. Min Act: -0.1700
Data Index: 3901879 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3628. Min Range: -6.3628
Max Act: 5.8315. Min Act: -0.1700
Data Index: 8028294 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3628. Min Range: -6.3628
Max Act: 5.8003. Min Act: -0.1700
Data Index: 5367459 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3628. Min Range: -6.3628
Max Act: 5.8003. Min Act: -0.1700
Data Index: 753119 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3628. Min Range: -6.3628
Max Act: 5.8003. Min Act: -0.1700
Data Index: 3385123 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3628. Min Range: -6.3628
Max Act: 5.8003. Min Act: -0.1700
Data Index: 5280540 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3628. Min Range: -6.3628
Max Act: 5.7690. Min Act: -0.1700
Data Index: 8119150 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3628. Min Range: -6.3628
Max Act: 5.7690. Min Act: -0.1700
Data Index: 1738003 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3628. Min Range: -6.3628
Max Act: 5.7690. Min Act: -0.1700
Data Index: 7038865 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19