Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3204 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2361. Min Range: -5.2361
Max Act: 5.2361. Min Act: -0.1700
Data Index: 2431594 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2361. Min Range: -5.2361
Max Act: 5.1424. Min Act: -0.1700
Data Index: 48949 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2361. Min Range: -5.2361
Max Act: 5.0799. Min Act: -0.1700
Data Index: 4607974 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2361. Min Range: -5.2361
Max Act: 4.9861. Min Act: -0.1700
Data Index: 5334530 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2361. Min Range: -5.2361
Max Act: 4.9549. Min Act: -0.1700
Data Index: 5619138 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2361. Min Range: -5.2361
Max Act: 4.9236. Min Act: -0.1700
Data Index: 6736298 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2361. Min Range: -5.2361
Max Act: 4.9236. Min Act: -0.1700
Data Index: 1783755 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2361. Min Range: -5.2361
Max Act: 4.8924. Min Act: -0.1700
Data Index: 4954500 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2361. Min Range: -5.2361
Max Act: 4.8611. Min Act: -0.1700
Data Index: 3998558 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2361. Min Range: -5.2361
Max Act: 4.9236. Min Act: -0.1700
Data Index: 8242493 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2361. Min Range: -5.2361
Max Act: 4.8924. Min Act: -0.1700
Data Index: 2106587 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2361. Min Range: -5.2361
Max Act: 4.8924. Min Act: -0.1700
Data Index: 5804445 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2361. Min Range: -5.2361
Max Act: 4.8611. Min Act: -0.1700
Data Index: 3054591 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2361. Min Range: -5.2361
Max Act: 4.8611. Min Act: -0.1700
Data Index: 4954510 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2361. Min Range: -5.2361
Max Act: 4.8299. Min Act: -0.1700
Data Index: 4710978 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2361. Min Range: -5.2361
Max Act: 4.8299. Min Act: -0.1700
Data Index: 5772675 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2361. Min Range: -5.2361
Max Act: 4.8299. Min Act: -0.1700
Data Index: 7135926 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2361. Min Range: -5.2361
Max Act: 4.7674. Min Act: -0.1700
Data Index: 3947264 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2361. Min Range: -5.2361
Max Act: 4.7986. Min Act: -0.1700
Data Index: 42252 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2361. Min Range: -5.2361
Max Act: 4.7361. Min Act: -0.1700
Data Index: 6184624 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #19