Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4192 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0883. Min Range: -6.0883
Max Act: 6.0883. Min Act: -0.1700
Data Index: 6370411 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0883. Min Range: -6.0883
Max Act: 5.8383. Min Act: -0.1700
Data Index: 5103796 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0883. Min Range: -6.0883
Max Act: 5.7445. Min Act: -0.1700
Data Index: 1528749 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0883. Min Range: -6.0883
Max Act: 5.7133. Min Act: -0.1700
Data Index: 4834185 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0883. Min Range: -6.0883
Max Act: 5.7133. Min Act: -0.1700
Data Index: 2004472 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0883. Min Range: -6.0883
Max Act: 5.6820. Min Act: -0.1700
Data Index: 459668 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0883. Min Range: -6.0883
Max Act: 5.6820. Min Act: -0.1700
Data Index: 1791638 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0883. Min Range: -6.0883
Max Act: 5.6820. Min Act: -0.1700
Data Index: 442936 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0883. Min Range: -6.0883
Max Act: 5.6820. Min Act: -0.1700
Data Index: 3209020 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0883. Min Range: -6.0883
Max Act: 5.6508. Min Act: -0.1700
Data Index: 3602811 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0883. Min Range: -6.0883
Max Act: 5.6508. Min Act: -0.1700
Data Index: 8778663 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0883. Min Range: -6.0883
Max Act: 5.6508. Min Act: -0.1700
Data Index: 2739627 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0883. Min Range: -6.0883
Max Act: 5.6195. Min Act: -0.1700
Data Index: 4347651 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0883. Min Range: -6.0883
Max Act: 5.5883. Min Act: -0.1700
Data Index: 553193 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0883. Min Range: -6.0883
Max Act: 5.5883. Min Act: -0.1700
Data Index: 1422643 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0883. Min Range: -6.0883
Max Act: 5.5570. Min Act: -0.1700
Data Index: 8694081 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0883. Min Range: -6.0883
Max Act: 5.5883. Min Act: -0.1700
Data Index: 5858947 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0883. Min Range: -6.0883
Max Act: 5.5570. Min Act: -0.1700
Data Index: 740690 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0883. Min Range: -6.0883
Max Act: 5.5570. Min Act: -0.1700
Data Index: 6960039 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0883. Min Range: -6.0883
Max Act: 5.5570. Min Act: -0.1700
Data Index: 7856054 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19