Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3323 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7353. Min Range: -5.7353
Max Act: 5.7353. Min Act: -0.1700
Data Index: 2342578 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7353. Min Range: -5.7353
Max Act: 5.6728. Min Act: -0.1700
Data Index: 1058656 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7353. Min Range: -5.7353
Max Act: 5.4853. Min Act: -0.1700
Data Index: 3474184 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7353. Min Range: -5.7353
Max Act: 5.3290. Min Act: -0.1700
Data Index: 4213006 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7353. Min Range: -5.7353
Max Act: 5.2665. Min Act: -0.1700
Data Index: 3896681 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7353. Min Range: -5.7353
Max Act: 5.1415. Min Act: -0.1700
Data Index: 3933039 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7353. Min Range: -5.7353
Max Act: 5.1415. Min Act: -0.1700
Data Index: 4660711 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7353. Min Range: -5.7353
Max Act: 5.1415. Min Act: -0.1700
Data Index: 1601787 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7353. Min Range: -5.7353
Max Act: 5.1103. Min Act: -0.1700
Data Index: 7409261 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7353. Min Range: -5.7353
Max Act: 5.0790. Min Act: -0.1700
Data Index: 7360022 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7353. Min Range: -5.7353
Max Act: 5.0478. Min Act: -0.1700
Data Index: 1324673 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7353. Min Range: -5.7353
Max Act: 5.0478. Min Act: -0.1700
Data Index: 1586696 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7353. Min Range: -5.7353
Max Act: 5.0165. Min Act: -0.1700
Data Index: 406030 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7353. Min Range: -5.7353
Max Act: 5.0165. Min Act: -0.1700
Data Index: 8081640 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7353. Min Range: -5.7353
Max Act: 5.0165. Min Act: -0.1700
Data Index: 5012608 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7353. Min Range: -5.7353
Max Act: 5.0165. Min Act: -0.1700
Data Index: 71875 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7353. Min Range: -5.7353
Max Act: 5.0165. Min Act: -0.1700
Data Index: 4520094 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7353. Min Range: -5.7353
Max Act: 5.0165. Min Act: -0.1700
Data Index: 814570 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7353. Min Range: -5.7353
Max Act: 4.9853. Min Act: -0.1700
Data Index: 2702432 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7353. Min Range: -5.7353
Max Act: 4.9853. Min Act: -0.1700
Data Index: 8368165 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #19