Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2040 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7962. Min Range: -4.7962
Max Act: 4.7962. Min Act: -0.1700
Data Index: 6846252 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7962. Min Range: -4.7962
Max Act: 4.7649. Min Act: -0.1699
Data Index: 4721228 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7962. Min Range: -4.7962
Max Act: 4.7962. Min Act: -0.1700
Data Index: 4108003 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7962. Min Range: -4.7962
Max Act: 4.7337. Min Act: -0.1700
Data Index: 5047380 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7962. Min Range: -4.7962
Max Act: 4.7337. Min Act: -0.1700
Data Index: 654851 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7962. Min Range: -4.7962
Max Act: 4.7337. Min Act: -0.1700
Data Index: 5613894 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7962. Min Range: -4.7962
Max Act: 4.6712. Min Act: -0.1700
Data Index: 8054609 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7962. Min Range: -4.7962
Max Act: 4.6712. Min Act: -0.1700
Data Index: 6846248 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7962. Min Range: -4.7962
Max Act: 4.6712. Min Act: -0.1700
Data Index: 1938216 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7962. Min Range: -4.7962
Max Act: 4.6399. Min Act: -0.1700
Data Index: 1112392 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7962. Min Range: -4.7962
Max Act: 4.6399. Min Act: -0.1700
Data Index: 7744258 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7962. Min Range: -4.7962
Max Act: 4.6399. Min Act: -0.1700
Data Index: 4036018 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7962. Min Range: -4.7962
Max Act: 4.6399. Min Act: -0.1700
Data Index: 993889 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7962. Min Range: -4.7962
Max Act: 4.6399. Min Act: -0.1700
Data Index: 7495199 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7962. Min Range: -4.7962
Max Act: 4.6399. Min Act: -0.1700
Data Index: 1925422 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7962. Min Range: -4.7962
Max Act: 4.6087. Min Act: -0.1700
Data Index: 993884 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7962. Min Range: -4.7962
Max Act: 4.5774. Min Act: -0.1700
Data Index: 246740 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7962. Min Range: -4.7962
Max Act: 4.6087. Min Act: -0.1700
Data Index: 246739 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7962. Min Range: -4.7962
Max Act: 4.6087. Min Act: -0.1700
Data Index: 6311288 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7962. Min Range: -4.7962
Max Act: 4.6087. Min Act: -0.1700
Data Index: 3254718 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19