Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 472 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4361. Min Range: -6.4361
Max Act: 6.4361. Min Act: -0.1700
Data Index: 7263796 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4361. Min Range: -6.4361
Max Act: 6.1236. Min Act: -0.1700
Data Index: 8691636 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4361. Min Range: -6.4361
Max Act: 6.0923. Min Act: -0.1700
Data Index: 4462142 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4361. Min Range: -6.4361
Max Act: 6.0298. Min Act: -0.1700
Data Index: 6106812 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4361. Min Range: -6.4361
Max Act: 6.0611. Min Act: -0.1700
Data Index: 2401807 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4361. Min Range: -6.4361
Max Act: 5.9361. Min Act: -0.1700
Data Index: 7707177 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4361. Min Range: -6.4361
Max Act: 5.9048. Min Act: -0.1700
Data Index: 4069744 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4361. Min Range: -6.4361
Max Act: 5.9048. Min Act: -0.1700
Data Index: 8325701 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4361. Min Range: -6.4361
Max Act: 5.8736. Min Act: -0.1700
Data Index: 4183915 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4361. Min Range: -6.4361
Max Act: 5.8423. Min Act: -0.1700
Data Index: 4386112 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4361. Min Range: -6.4361
Max Act: 5.8423. Min Act: -0.1700
Data Index: 2051138 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4361. Min Range: -6.4361
Max Act: 5.8111. Min Act: -0.1700
Data Index: 6339468 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4361. Min Range: -6.4361
Max Act: 5.8111. Min Act: -0.1700
Data Index: 4888671 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4361. Min Range: -6.4361
Max Act: 5.8736. Min Act: -0.1700
Data Index: 2772862 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4361. Min Range: -6.4361
Max Act: 5.8111. Min Act: -0.1700
Data Index: 8362123 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4361. Min Range: -6.4361
Max Act: 5.7798. Min Act: -0.1700
Data Index: 2809823 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4361. Min Range: -6.4361
Max Act: 5.7798. Min Act: -0.1700
Data Index: 8434478 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4361. Min Range: -6.4361
Max Act: 5.7798. Min Act: -0.1700
Data Index: 6438775 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4361. Min Range: -6.4361
Max Act: 5.7798. Min Act: -0.1700
Data Index: 5324703 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4361. Min Range: -6.4361
Max Act: 5.7486. Min Act: -0.1700
Data Index: 1295475 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #19