Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3772 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7612. Min Range: -5.7612
Max Act: 5.7612. Min Act: -0.1700
Data Index: 6408607 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7612. Min Range: -5.7612
Max Act: 5.2612. Min Act: -0.1700
Data Index: 7942118 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7612. Min Range: -5.7612
Max Act: 5.1362. Min Act: -0.1700
Data Index: 5118794 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7612. Min Range: -5.7612
Max Act: 5.1050. Min Act: -0.1700
Data Index: 2185992 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7612. Min Range: -5.7612
Max Act: 5.1362. Min Act: -0.1700
Data Index: 1153129 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7612. Min Range: -5.7612
Max Act: 5.0425. Min Act: -0.1700
Data Index: 3305647 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7612. Min Range: -5.7612
Max Act: 5.0425. Min Act: -0.1700
Data Index: 251013 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7612. Min Range: -5.7612
Max Act: 4.9800. Min Act: -0.1700
Data Index: 4907780 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7612. Min Range: -5.7612
Max Act: 4.9800. Min Act: -0.1700
Data Index: 4618374 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7612. Min Range: -5.7612
Max Act: 4.9800. Min Act: -0.1700
Data Index: 8411116 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7612. Min Range: -5.7612
Max Act: 4.9487. Min Act: -0.1700
Data Index: 67487 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7612. Min Range: -5.7612
Max Act: 4.9175. Min Act: -0.1700
Data Index: 5880306 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7612. Min Range: -5.7612
Max Act: 4.8862. Min Act: -0.1700
Data Index: 8478385 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7612. Min Range: -5.7612
Max Act: 4.8862. Min Act: -0.1700
Data Index: 7876401 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7612. Min Range: -5.7612
Max Act: 4.8862. Min Act: -0.1700
Data Index: 115612 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7612. Min Range: -5.7612
Max Act: 4.8862. Min Act: -0.1700
Data Index: 5416806 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7612. Min Range: -5.7612
Max Act: 4.8862. Min Act: -0.1700
Data Index: 3720246 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7612. Min Range: -5.7612
Max Act: 4.8237. Min Act: -0.1700
Data Index: 301801 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7612. Min Range: -5.7612
Max Act: 4.8862. Min Act: -0.1700
Data Index: 8085 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7612. Min Range: -5.7612
Max Act: 4.8550. Min Act: -0.1700
Data Index: 7971535 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19