Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3424 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1792. Min Range: -8.1792
Max Act: 8.1792. Min Act: -0.1700
Data Index: 4487072 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1792. Min Range: -8.1792
Max Act: 7.6167. Min Act: -0.1700
Data Index: 8302377 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1792. Min Range: -8.1792
Max Act: 7.5855. Min Act: -0.1700
Data Index: 6160486 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1792. Min Range: -8.1792
Max Act: 7.5542. Min Act: -0.1700
Data Index: 6559119 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1792. Min Range: -8.1792
Max Act: 7.5542. Min Act: -0.1700
Data Index: 7020540 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1792. Min Range: -8.1792
Max Act: 7.5542. Min Act: -0.1700
Data Index: 3576273 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1792. Min Range: -8.1792
Max Act: 7.4917. Min Act: -0.1700
Data Index: 4010881 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1792. Min Range: -8.1792
Max Act: 7.4917. Min Act: -0.1700
Data Index: 6886065 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1792. Min Range: -8.1792
Max Act: 7.3980. Min Act: -0.1700
Data Index: 1010234 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1792. Min Range: -8.1792
Max Act: 7.3980. Min Act: -0.1700
Data Index: 1682504 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1792. Min Range: -8.1792
Max Act: 7.3667. Min Act: -0.1700
Data Index: 5858861 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1792. Min Range: -8.1792
Max Act: 7.3667. Min Act: -0.1700
Data Index: 8446802 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1792. Min Range: -8.1792
Max Act: 7.3355. Min Act: -0.1700
Data Index: 5446351 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1792. Min Range: -8.1792
Max Act: 7.3355. Min Act: -0.1700
Data Index: 4110699 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1792. Min Range: -8.1792
Max Act: 7.3355. Min Act: -0.1700
Data Index: 3416872 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1792. Min Range: -8.1792
Max Act: 7.3355. Min Act: -0.1700
Data Index: 5633445 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1792. Min Range: -8.1792
Max Act: 7.3355. Min Act: -0.1700
Data Index: 8736564 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1792. Min Range: -8.1792
Max Act: 7.3042. Min Act: -0.1700
Data Index: 2275445 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1792. Min Range: -8.1792
Max Act: 7.3042. Min Act: -0.1700
Data Index: 6863658 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1792. Min Range: -8.1792
Max Act: 7.3042. Min Act: -0.1700
Data Index: 2330721 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #19