Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2176 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4526. Min Range: -6.4526
Max Act: 6.4526. Min Act: -0.1700
Data Index: 5546821 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4526. Min Range: -6.4526
Max Act: 6.2026. Min Act: -0.1700
Data Index: 8357412 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4526. Min Range: -6.4526
Max Act: 6.1088. Min Act: -0.1700
Data Index: 4100436 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4526. Min Range: -6.4526
Max Act: 6.0463. Min Act: -0.1700
Data Index: 2643962 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4526. Min Range: -6.4526
Max Act: 6.0151. Min Act: -0.1700
Data Index: 12189 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4526. Min Range: -6.4526
Max Act: 6.0463. Min Act: -0.1700
Data Index: 3656665 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4526. Min Range: -6.4526
Max Act: 5.9838. Min Act: -0.1700
Data Index: 8523836 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4526. Min Range: -6.4526
Max Act: 6.0151. Min Act: -0.1700
Data Index: 3399760 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4526. Min Range: -6.4526
Max Act: 6.0151. Min Act: -0.1700
Data Index: 8543351 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4526. Min Range: -6.4526
Max Act: 5.9838. Min Act: -0.1700
Data Index: 414596 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4526. Min Range: -6.4526
Max Act: 5.9526. Min Act: -0.1700
Data Index: 7031102 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4526. Min Range: -6.4526
Max Act: 5.9213. Min Act: -0.1700
Data Index: 7039939 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4526. Min Range: -6.4526
Max Act: 5.8901. Min Act: -0.1700
Data Index: 6023048 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4526. Min Range: -6.4526
Max Act: 5.8588. Min Act: -0.1700
Data Index: 7846576 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4526. Min Range: -6.4526
Max Act: 5.8276. Min Act: -0.1700
Data Index: 331158 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4526. Min Range: -6.4526
Max Act: 5.7963. Min Act: -0.1700
Data Index: 2729567 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4526. Min Range: -6.4526
Max Act: 5.8276. Min Act: -0.1700
Data Index: 8034014 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4526. Min Range: -6.4526
Max Act: 5.7651. Min Act: -0.1700
Data Index: 4266989 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4526. Min Range: -6.4526
Max Act: 5.7651. Min Act: -0.1700
Data Index: 660313 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4526. Min Range: -6.4526
Max Act: 5.7651. Min Act: -0.1700
Data Index: 20418 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #19