Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4827 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7339. Min Range: -5.7339
Max Act: 5.7339. Min Act: -0.1700
Data Index: 1506331 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7339. Min Range: -5.7339
Max Act: 5.6401. Min Act: -0.1700
Data Index: 5834444 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7339. Min Range: -5.7339
Max Act: 5.6401. Min Act: -0.1700
Data Index: 7625739 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7339. Min Range: -5.7339
Max Act: 5.6089. Min Act: -0.1700
Data Index: 4182252 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7339. Min Range: -5.7339
Max Act: 5.5776. Min Act: -0.1700
Data Index: 2387660 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7339. Min Range: -5.7339
Max Act: 5.5776. Min Act: -0.1700
Data Index: 2506928 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7339. Min Range: -5.7339
Max Act: 5.5776. Min Act: -0.1700
Data Index: 1705465 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7339. Min Range: -5.7339
Max Act: 5.5464. Min Act: -0.1700
Data Index: 720102 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7339. Min Range: -5.7339
Max Act: 5.5151. Min Act: -0.1700
Data Index: 483997 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7339. Min Range: -5.7339
Max Act: 5.5464. Min Act: -0.1700
Data Index: 487857 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7339. Min Range: -5.7339
Max Act: 5.5151. Min Act: -0.1700
Data Index: 4199080 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7339. Min Range: -5.7339
Max Act: 5.5151. Min Act: -0.1700
Data Index: 1230477 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7339. Min Range: -5.7339
Max Act: 5.4839. Min Act: -0.1700
Data Index: 3947788 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7339. Min Range: -5.7339
Max Act: 5.4526. Min Act: -0.1700
Data Index: 3521298 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7339. Min Range: -5.7339
Max Act: 5.4839. Min Act: -0.1700
Data Index: 2657603 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7339. Min Range: -5.7339
Max Act: 5.4526. Min Act: -0.1700
Data Index: 3236532 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7339. Min Range: -5.7339
Max Act: 5.4839. Min Act: -0.1700
Data Index: 636290 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7339. Min Range: -5.7339
Max Act: 5.4839. Min Act: -0.1700
Data Index: 1850732 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7339. Min Range: -5.7339
Max Act: 5.4839. Min Act: -0.1700
Data Index: 4517965 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7339. Min Range: -5.7339
Max Act: 5.4526. Min Act: -0.1700
Data Index: 183501 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #19