Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3024 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8209. Min Range: -7.8209
Max Act: 7.8209. Min Act: -0.1700
Data Index: 3846820 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8209. Min Range: -7.8209
Max Act: 7.6021. Min Act: -0.1700
Data Index: 3860075 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8209. Min Range: -7.8209
Max Act: 7.4459. Min Act: -0.1700
Data Index: 2226030 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8209. Min Range: -7.8209
Max Act: 7.3834. Min Act: -0.1700
Data Index: 8444418 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8209. Min Range: -7.8209
Max Act: 7.1646. Min Act: -0.1700
Data Index: 3075033 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8209. Min Range: -7.8209
Max Act: 7.1334. Min Act: -0.1700
Data Index: 6149714 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8209. Min Range: -7.8209
Max Act: 7.0709. Min Act: -0.1700
Data Index: 6114716 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8209. Min Range: -7.8209
Max Act: 7.0709. Min Act: -0.1700
Data Index: 3618851 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8209. Min Range: -7.8209
Max Act: 7.0709. Min Act: -0.1700
Data Index: 255817 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8209. Min Range: -7.8209
Max Act: 7.0396. Min Act: -0.1700
Data Index: 8087962 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8209. Min Range: -7.8209
Max Act: 6.9459. Min Act: -0.1700
Data Index: 6909353 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8209. Min Range: -7.8209
Max Act: 6.9459. Min Act: -0.1700
Data Index: 2559267 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8209. Min Range: -7.8209
Max Act: 6.9459. Min Act: -0.1700
Data Index: 4400847 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8209. Min Range: -7.8209
Max Act: 6.9459. Min Act: -0.1700
Data Index: 151066 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8209. Min Range: -7.8209
Max Act: 6.9146. Min Act: -0.1700
Data Index: 6485068 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8209. Min Range: -7.8209
Max Act: 6.9146. Min Act: -0.1700
Data Index: 8305392 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8209. Min Range: -7.8209
Max Act: 6.8834. Min Act: -0.1700
Data Index: 6149719 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8209. Min Range: -7.8209
Max Act: 6.8521. Min Act: -0.1700
Data Index: 5622814 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8209. Min Range: -7.8209
Max Act: 6.8521. Min Act: -0.1700
Data Index: 5879191 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8209. Min Range: -7.8209
Max Act: 6.7896. Min Act: -0.1700
Data Index: 5622816 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #19