Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3096 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8121. Min Range: -6.8121
Max Act: 6.8121. Min Act: -0.1700
Data Index: 4026896 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8121. Min Range: -6.8121
Max Act: 6.7496. Min Act: -0.1700
Data Index: 1130250 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8121. Min Range: -6.8121
Max Act: 6.6871. Min Act: -0.1700
Data Index: 2022331 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8121. Min Range: -6.8121
Max Act: 6.6559. Min Act: -0.1700
Data Index: 1027500 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8121. Min Range: -6.8121
Max Act: 6.5934. Min Act: -0.1700
Data Index: 7276991 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8121. Min Range: -6.8121
Max Act: 6.5621. Min Act: -0.1700
Data Index: 7054941 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8121. Min Range: -6.8121
Max Act: 6.5621. Min Act: -0.1700
Data Index: 7816911 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8121. Min Range: -6.8121
Max Act: 6.5309. Min Act: -0.1700
Data Index: 1602764 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8121. Min Range: -6.8121
Max Act: 6.5309. Min Act: -0.1700
Data Index: 863744 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8121. Min Range: -6.8121
Max Act: 6.4996. Min Act: -0.1700
Data Index: 8618908 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8121. Min Range: -6.8121
Max Act: 6.4684. Min Act: -0.1700
Data Index: 3179862 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8121. Min Range: -6.8121
Max Act: 6.4684. Min Act: -0.1700
Data Index: 7150123 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8121. Min Range: -6.8121
Max Act: 6.4684. Min Act: -0.1700
Data Index: 2454504 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8121. Min Range: -6.8121
Max Act: 6.4371. Min Act: -0.1700
Data Index: 4982667 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8121. Min Range: -6.8121
Max Act: 6.4059. Min Act: -0.1700
Data Index: 5696273 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8121. Min Range: -6.8121
Max Act: 6.4059. Min Act: -0.1700
Data Index: 3940391 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8121. Min Range: -6.8121
Max Act: 6.4371. Min Act: -0.1700
Data Index: 2963256 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8121. Min Range: -6.8121
Max Act: 6.3746. Min Act: -0.1700
Data Index: 3117456 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8121. Min Range: -6.8121
Max Act: 6.3434. Min Act: -0.1700
Data Index: 4181179 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8121. Min Range: -6.8121
Max Act: 6.3434. Min Act: -0.1700
Data Index: 6883507 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #19