Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6250 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3395. Min Range: -9.3395
Max Act: 9.3395. Min Act: -0.1700
Data Index: 4394668 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3395. Min Range: -9.3395
Max Act: 9.0895. Min Act: -0.1700
Data Index: 1994510 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3395. Min Range: -9.3395
Max Act: 9.0895. Min Act: -0.1700
Data Index: 3647150 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3395. Min Range: -9.3395
Max Act: 9.0270. Min Act: -0.1700
Data Index: 5780432 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3395. Min Range: -9.3395
Max Act: 9.0270. Min Act: -0.1700
Data Index: 2988975 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3395. Min Range: -9.3395
Max Act: 8.9645. Min Act: -0.1700
Data Index: 5396617 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3395. Min Range: -9.3395
Max Act: 8.9645. Min Act: -0.1700
Data Index: 1301206 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3395. Min Range: -9.3395
Max Act: 8.9645. Min Act: -0.1700
Data Index: 1394693 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3395. Min Range: -9.3395
Max Act: 8.9020. Min Act: -0.1700
Data Index: 1885320 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3395. Min Range: -9.3395
Max Act: 8.8395. Min Act: -0.1700
Data Index: 5770950 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3395. Min Range: -9.3395
Max Act: 8.9020. Min Act: -0.1700
Data Index: 3227663 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3395. Min Range: -9.3395
Max Act: 8.9020. Min Act: -0.1700
Data Index: 3523986 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3395. Min Range: -9.3395
Max Act: 8.8395. Min Act: -0.1700
Data Index: 6008447 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3395. Min Range: -9.3395
Max Act: 8.7770. Min Act: -0.1700
Data Index: 1660770 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3395. Min Range: -9.3395
Max Act: 8.8395. Min Act: -0.1700
Data Index: 8028255 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3395. Min Range: -9.3395
Max Act: 8.8395. Min Act: -0.1700
Data Index: 1886645 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3395. Min Range: -9.3395
Max Act: 8.7770. Min Act: -0.1700
Data Index: 4345446 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3395. Min Range: -9.3395
Max Act: 8.7770. Min Act: -0.1700
Data Index: 1818027 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3395. Min Range: -9.3395
Max Act: 8.7145. Min Act: -0.1700
Data Index: 3168167 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3395. Min Range: -9.3395
Max Act: 8.7145. Min Act: -0.1700
Data Index: 5949411 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #19