Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3462 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4433. Min Range: -7.4433
Max Act: 7.4433. Min Act: -0.1700
Data Index: 8496421 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4433. Min Range: -7.4433
Max Act: 7.4121. Min Act: -0.1700
Data Index: 2238700 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4433. Min Range: -7.4433
Max Act: 7.3496. Min Act: -0.1700
Data Index: 8462041 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4433. Min Range: -7.4433
Max Act: 7.3496. Min Act: -0.1700
Data Index: 1114209 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4433. Min Range: -7.4433
Max Act: 7.2871. Min Act: -0.1700
Data Index: 1899022 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4433. Min Range: -7.4433
Max Act: 7.2871. Min Act: -0.1700
Data Index: 4112118 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4433. Min Range: -7.4433
Max Act: 7.2558. Min Act: -0.1700
Data Index: 3391755 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4433. Min Range: -7.4433
Max Act: 7.2558. Min Act: -0.1700
Data Index: 609554 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4433. Min Range: -7.4433
Max Act: 7.1933. Min Act: -0.1700
Data Index: 2517361 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4433. Min Range: -7.4433
Max Act: 7.1621. Min Act: -0.1700
Data Index: 681541 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4433. Min Range: -7.4433
Max Act: 7.1308. Min Act: -0.1700
Data Index: 2831927 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4433. Min Range: -7.4433
Max Act: 7.1308. Min Act: -0.1700
Data Index: 5758167 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4433. Min Range: -7.4433
Max Act: 7.1308. Min Act: -0.1700
Data Index: 2367923 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4433. Min Range: -7.4433
Max Act: 7.0996. Min Act: -0.1700
Data Index: 226639 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4433. Min Range: -7.4433
Max Act: 7.0683. Min Act: -0.1700
Data Index: 7678380 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4433. Min Range: -7.4433
Max Act: 7.0683. Min Act: -0.1700
Data Index: 215004 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4433. Min Range: -7.4433
Max Act: 7.0683. Min Act: -0.1700
Data Index: 4520125 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4433. Min Range: -7.4433
Max Act: 7.0371. Min Act: -0.1700
Data Index: 2868931 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4433. Min Range: -7.4433
Max Act: 7.0683. Min Act: -0.1700
Data Index: 8462040 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4433. Min Range: -7.4433
Max Act: 7.0371. Min Act: -0.1700
Data Index: 552868 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #19