Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2628 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8729. Min Range: -7.8729
Max Act: 7.8729. Min Act: -0.1700
Data Index: 7052590 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8729. Min Range: -7.8729
Max Act: 7.8104. Min Act: -0.1700
Data Index: 8568714 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8729. Min Range: -7.8729
Max Act: 7.7479. Min Act: -0.1700
Data Index: 8317365 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8729. Min Range: -7.8729
Max Act: 7.4979. Min Act: -0.1700
Data Index: 4670585 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8729. Min Range: -7.8729
Max Act: 7.4042. Min Act: -0.1700
Data Index: 622902 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8729. Min Range: -7.8729
Max Act: 7.4042. Min Act: -0.1700
Data Index: 4177581 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8729. Min Range: -7.8729
Max Act: 7.3729. Min Act: -0.1700
Data Index: 6792565 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8729. Min Range: -7.8729
Max Act: 7.3417. Min Act: -0.1700
Data Index: 6725650 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8729. Min Range: -7.8729
Max Act: 7.2792. Min Act: -0.1700
Data Index: 6866501 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8729. Min Range: -7.8729
Max Act: 7.2167. Min Act: -0.1700
Data Index: 2391390 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8729. Min Range: -7.8729
Max Act: 7.1854. Min Act: -0.1700
Data Index: 5896198 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8729. Min Range: -7.8729
Max Act: 7.1854. Min Act: -0.1700
Data Index: 3178954 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8729. Min Range: -7.8729
Max Act: 7.1229. Min Act: -0.1700
Data Index: 3804360 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8729. Min Range: -7.8729
Max Act: 7.0604. Min Act: -0.1700
Data Index: 292900 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8729. Min Range: -7.8729
Max Act: 7.0917. Min Act: -0.1700
Data Index: 6826597 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8729. Min Range: -7.8729
Max Act: 7.0604. Min Act: -0.1700
Data Index: 1124760 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8729. Min Range: -7.8729
Max Act: 7.0604. Min Act: -0.1700
Data Index: 7883464 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8729. Min Range: -7.8729
Max Act: 7.0292. Min Act: -0.1700
Data Index: 2990742 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8729. Min Range: -7.8729
Max Act: 7.0292. Min Act: -0.1700
Data Index: 7637334 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8729. Min Range: -7.8729
Max Act: 7.0292. Min Act: -0.1700
Data Index: 3442570 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19