Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3549 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5184. Min Range: -7.5184
Max Act: 7.5184. Min Act: -0.1700
Data Index: 3666455 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5184. Min Range: -7.5184
Max Act: 7.4247. Min Act: -0.1700
Data Index: 5422483 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5184. Min Range: -7.5184
Max Act: 7.3622. Min Act: -0.1700
Data Index: 4297760 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5184. Min Range: -7.5184
Max Act: 7.3622. Min Act: -0.1700
Data Index: 6857904 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5184. Min Range: -7.5184
Max Act: 7.3622. Min Act: -0.1700
Data Index: 5975799 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5184. Min Range: -7.5184
Max Act: 7.2997. Min Act: -0.1700
Data Index: 4588857 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5184. Min Range: -7.5184
Max Act: 7.2059. Min Act: -0.1700
Data Index: 2561641 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5184. Min Range: -7.5184
Max Act: 7.2059. Min Act: -0.1700
Data Index: 8319452 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5184. Min Range: -7.5184
Max Act: 7.2059. Min Act: -0.1700
Data Index: 1916294 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5184. Min Range: -7.5184
Max Act: 7.2059. Min Act: -0.1700
Data Index: 5638568 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5184. Min Range: -7.5184
Max Act: 7.1747. Min Act: -0.1700
Data Index: 4846147 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5184. Min Range: -7.5184
Max Act: 7.2059. Min Act: -0.1700
Data Index: 8708182 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5184. Min Range: -7.5184
Max Act: 7.2372. Min Act: -0.1700
Data Index: 4316235 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5184. Min Range: -7.5184
Max Act: 7.2059. Min Act: -0.1700
Data Index: 2322675 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5184. Min Range: -7.5184
Max Act: 7.1747. Min Act: -0.1700
Data Index: 5299322 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5184. Min Range: -7.5184
Max Act: 7.1434. Min Act: -0.1700
Data Index: 2625139 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5184. Min Range: -7.5184
Max Act: 7.1434. Min Act: -0.1700
Data Index: 4368334 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5184. Min Range: -7.5184
Max Act: 7.1434. Min Act: -0.1700
Data Index: 7184466 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5184. Min Range: -7.5184
Max Act: 7.1122. Min Act: -0.1700
Data Index: 6471368 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5184. Min Range: -7.5184
Max Act: 7.1122. Min Act: -0.1700
Data Index: 2765406 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #19