Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3068 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9653. Min Range: -5.9653
Max Act: 5.9653. Min Act: -0.1700
Data Index: 2422366 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9653. Min Range: -5.9653
Max Act: 5.4966. Min Act: -0.1700
Data Index: 4124244 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9653. Min Range: -5.9653
Max Act: 5.4966. Min Act: -0.1700
Data Index: 1041015 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9653. Min Range: -5.9653
Max Act: 5.4028. Min Act: -0.1700
Data Index: 5161597 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9653. Min Range: -5.9653
Max Act: 5.4028. Min Act: -0.1700
Data Index: 641909 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9653. Min Range: -5.9653
Max Act: 5.3716. Min Act: -0.1700
Data Index: 5627027 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9653. Min Range: -5.9653
Max Act: 5.3716. Min Act: -0.1700
Data Index: 2692412 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9653. Min Range: -5.9653
Max Act: 5.3716. Min Act: -0.1700
Data Index: 6774695 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9653. Min Range: -5.9653
Max Act: 5.3716. Min Act: -0.1700
Data Index: 7125912 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9653. Min Range: -5.9653
Max Act: 5.3716. Min Act: -0.1700
Data Index: 4328925 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9653. Min Range: -5.9653
Max Act: 5.3403. Min Act: -0.1700
Data Index: 5341732 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9653. Min Range: -5.9653
Max Act: 5.3091. Min Act: -0.1700
Data Index: 460714 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9653. Min Range: -5.9653
Max Act: 5.3403. Min Act: -0.1700
Data Index: 703076 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9653. Min Range: -5.9653
Max Act: 5.3091. Min Act: -0.1700
Data Index: 6633848 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9653. Min Range: -5.9653
Max Act: 5.3091. Min Act: -0.1700
Data Index: 3028717 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9653. Min Range: -5.9653
Max Act: 5.2778. Min Act: -0.1700
Data Index: 6731822 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9653. Min Range: -5.9653
Max Act: 5.2778. Min Act: -0.1700
Data Index: 1909487 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9653. Min Range: -5.9653
Max Act: 5.2778. Min Act: -0.1700
Data Index: 7069170 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9653. Min Range: -5.9653
Max Act: 5.2778. Min Act: -0.1700
Data Index: 7165903 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9653. Min Range: -5.9653
Max Act: 5.2778. Min Act: -0.1700
Data Index: 3693049 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #19