Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4352 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4871. Min Range: -4.4871
Max Act: 4.4871. Min Act: -0.1700
Data Index: 1249466 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4871. Min Range: -4.4871
Max Act: 4.1433. Min Act: -0.1700
Data Index: 5634194 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4871. Min Range: -4.4871
Max Act: 4.0808. Min Act: -0.1700
Data Index: 3244764 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4871. Min Range: -4.4871
Max Act: 4.1120. Min Act: -0.1700
Data Index: 2891939 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4871. Min Range: -4.4871
Max Act: 4.0182. Min Act: -0.1700
Data Index: 4565330 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4871. Min Range: -4.4871
Max Act: 4.0182. Min Act: -0.1700
Data Index: 7388696 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4871. Min Range: -4.4871
Max Act: 4.0182. Min Act: -0.1700
Data Index: 949038 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4871. Min Range: -4.4871
Max Act: 4.0182. Min Act: -0.1700
Data Index: 8565624 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4871. Min Range: -4.4871
Max Act: 3.9245. Min Act: -0.1700
Data Index: 1203177 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4871. Min Range: -4.4871
Max Act: 3.9245. Min Act: -0.1700
Data Index: 1828944 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4871. Min Range: -4.4871
Max Act: 3.9245. Min Act: -0.1700
Data Index: 4766404 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4871. Min Range: -4.4871
Max Act: 3.9245. Min Act: -0.1700
Data Index: 6753336 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4871. Min Range: -4.4871
Max Act: 3.8932. Min Act: -0.1700
Data Index: 1733997 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4871. Min Range: -4.4871
Max Act: 3.8932. Min Act: -0.1700
Data Index: 722117 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4871. Min Range: -4.4871
Max Act: 3.8619. Min Act: -0.1700
Data Index: 5904470 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4871. Min Range: -4.4871
Max Act: 3.8619. Min Act: -0.1700
Data Index: 7583682 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4871. Min Range: -4.4871
Max Act: 3.8619. Min Act: -0.1700
Data Index: 3344870 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4871. Min Range: -4.4871
Max Act: 3.8619. Min Act: -0.1700
Data Index: 88168 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4871. Min Range: -4.4871
Max Act: 3.8307. Min Act: -0.1700
Data Index: 5857717 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4871. Min Range: -4.4871
Max Act: 3.8307. Min Act: -0.1700
Data Index: 5902383 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #19