Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4502 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8373. Min Range: -5.8373
Max Act: 5.8373. Min Act: -0.1700
Data Index: 3648598 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8373. Min Range: -5.8373
Max Act: 5.6498. Min Act: -0.1700
Data Index: 847976 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8373. Min Range: -5.8373
Max Act: 5.5560. Min Act: -0.1700
Data Index: 8532738 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8373. Min Range: -5.8373
Max Act: 5.4935. Min Act: -0.1700
Data Index: 1060434 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8373. Min Range: -5.8373
Max Act: 5.4935. Min Act: -0.1700
Data Index: 6645675 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8373. Min Range: -5.8373
Max Act: 5.4310. Min Act: -0.1700
Data Index: 8593761 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8373. Min Range: -5.8373
Max Act: 5.4310. Min Act: -0.1700
Data Index: 7508901 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8373. Min Range: -5.8373
Max Act: 5.3373. Min Act: -0.1700
Data Index: 2236771 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8373. Min Range: -5.8373
Max Act: 5.3373. Min Act: -0.1700
Data Index: 3849366 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8373. Min Range: -5.8373
Max Act: 5.3060. Min Act: -0.1700
Data Index: 7661676 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8373. Min Range: -5.8373
Max Act: 5.3060. Min Act: -0.1700
Data Index: 1158815 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8373. Min Range: -5.8373
Max Act: 5.2435. Min Act: -0.1700
Data Index: 1200508 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8373. Min Range: -5.8373
Max Act: 5.2123. Min Act: -0.1700
Data Index: 7307801 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8373. Min Range: -5.8373
Max Act: 5.1498. Min Act: -0.1700
Data Index: 3747624 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8373. Min Range: -5.8373
Max Act: 5.1810. Min Act: -0.1700
Data Index: 5731323 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8373. Min Range: -5.8373
Max Act: 5.1810. Min Act: -0.1700
Data Index: 7227854 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8373. Min Range: -5.8373
Max Act: 5.1810. Min Act: -0.1700
Data Index: 5268922 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8373. Min Range: -5.8373
Max Act: 5.1498. Min Act: -0.1700
Data Index: 5091446 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8373. Min Range: -5.8373
Max Act: 5.1498. Min Act: -0.1700
Data Index: 3472586 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8373. Min Range: -5.8373
Max Act: 5.1498. Min Act: -0.1700
Data Index: 2627962 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19