Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3099 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8659. Min Range: -5.8659
Max Act: 5.8659. Min Act: -0.1700
Data Index: 6211165 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8659. Min Range: -5.8659
Max Act: 5.8659. Min Act: -0.1700
Data Index: 554005 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8659. Min Range: -5.8659
Max Act: 5.8346. Min Act: -0.1700
Data Index: 2483423 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8659. Min Range: -5.8659
Max Act: 5.7721. Min Act: -0.1700
Data Index: 7846679 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8659. Min Range: -5.8659
Max Act: 5.7721. Min Act: -0.1700
Data Index: 553965 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8659. Min Range: -5.8659
Max Act: 5.7409. Min Act: -0.1700
Data Index: 4584313 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8659. Min Range: -5.8659
Max Act: 5.7409. Min Act: -0.1700
Data Index: 553993 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8659. Min Range: -5.8659
Max Act: 5.6784. Min Act: -0.1700
Data Index: 7498119 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8659. Min Range: -5.8659
Max Act: 5.6471. Min Act: -0.1700
Data Index: 7785969 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8659. Min Range: -5.8659
Max Act: 5.6471. Min Act: -0.1700
Data Index: 7785968 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8659. Min Range: -5.8659
Max Act: 5.6471. Min Act: -0.1700
Data Index: 4596775 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8659. Min Range: -5.8659
Max Act: 5.6471. Min Act: -0.1700
Data Index: 4744684 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8659. Min Range: -5.8659
Max Act: 5.6159. Min Act: -0.1700
Data Index: 6674639 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8659. Min Range: -5.8659
Max Act: 5.5846. Min Act: -0.1700
Data Index: 6351486 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8659. Min Range: -5.8659
Max Act: 5.5846. Min Act: -0.1700
Data Index: 7785989 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8659. Min Range: -5.8659
Max Act: 5.5846. Min Act: -0.1700
Data Index: 3038948 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8659. Min Range: -5.8659
Max Act: 5.5534. Min Act: -0.1700
Data Index: 7364922 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8659. Min Range: -5.8659
Max Act: 5.5846. Min Act: -0.1700
Data Index: 554000 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8659. Min Range: -5.8659
Max Act: 5.5846. Min Act: -0.1700
Data Index: 7846680 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8659. Min Range: -5.8659
Max Act: 5.5846. Min Act: -0.1700
Data Index: 2354442 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #19