Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3824 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8375. Min Range: -5.8375
Max Act: 5.8375. Min Act: -0.1700
Data Index: 2321433 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8375. Min Range: -5.8375
Max Act: 5.7125. Min Act: -0.1700
Data Index: 689833 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8375. Min Range: -5.8375
Max Act: 5.7125. Min Act: -0.1700
Data Index: 7537179 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8375. Min Range: -5.8375
Max Act: 5.5875. Min Act: -0.1700
Data Index: 2448491 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8375. Min Range: -5.8375
Max Act: 5.5250. Min Act: -0.1700
Data Index: 7605357 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8375. Min Range: -5.8375
Max Act: 5.5250. Min Act: -0.1700
Data Index: 590629 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8375. Min Range: -5.8375
Max Act: 5.5250. Min Act: -0.1700
Data Index: 1555227 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8375. Min Range: -5.8375
Max Act: 5.4625. Min Act: -0.1700
Data Index: 8434751 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8375. Min Range: -5.8375
Max Act: 5.4313. Min Act: -0.1700
Data Index: 6026524 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8375. Min Range: -5.8375
Max Act: 5.4313. Min Act: -0.1700
Data Index: 7662100 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8375. Min Range: -5.8375
Max Act: 5.4313. Min Act: -0.1700
Data Index: 419536 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8375. Min Range: -5.8375
Max Act: 5.4000. Min Act: -0.1700
Data Index: 3445413 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8375. Min Range: -5.8375
Max Act: 5.4000. Min Act: -0.1700
Data Index: 703153 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8375. Min Range: -5.8375
Max Act: 5.3688. Min Act: -0.1700
Data Index: 4094992 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8375. Min Range: -5.8375
Max Act: 5.4313. Min Act: -0.1700
Data Index: 6638202 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8375. Min Range: -5.8375
Max Act: 5.4000. Min Act: -0.1700
Data Index: 3086353 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8375. Min Range: -5.8375
Max Act: 5.3688. Min Act: -0.1700
Data Index: 316435 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8375. Min Range: -5.8375
Max Act: 5.3688. Min Act: -0.1700
Data Index: 5435700 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8375. Min Range: -5.8375
Max Act: 5.3688. Min Act: -0.1700
Data Index: 6253405 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8375. Min Range: -5.8375
Max Act: 5.3375. Min Act: -0.1700
Data Index: 6192647 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #19