Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4516 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6249. Min Range: -7.6249
Max Act: 7.6249. Min Act: -0.1700
Data Index: 818613 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6249. Min Range: -7.6249
Max Act: 7.2187. Min Act: -0.1700
Data Index: 1765332 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6249. Min Range: -7.6249
Max Act: 7.1562. Min Act: -0.1700
Data Index: 1767487 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6249. Min Range: -7.6249
Max Act: 7.0937. Min Act: -0.1700
Data Index: 3325556 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6249. Min Range: -7.6249
Max Act: 7.0937. Min Act: -0.1700
Data Index: 1847594 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6249. Min Range: -7.6249
Max Act: 7.0937. Min Act: -0.1700
Data Index: 6937099 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6249. Min Range: -7.6249
Max Act: 6.9999. Min Act: -0.1700
Data Index: 690277 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6249. Min Range: -7.6249
Max Act: 6.9687. Min Act: -0.1700
Data Index: 6266774 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6249. Min Range: -7.6249
Max Act: 6.9062. Min Act: -0.1700
Data Index: 3558093 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6249. Min Range: -7.6249
Max Act: 6.9374. Min Act: -0.1700
Data Index: 5834719 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6249. Min Range: -7.6249
Max Act: 6.8749. Min Act: -0.1700
Data Index: 3533825 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6249. Min Range: -7.6249
Max Act: 6.8749. Min Act: -0.1700
Data Index: 291750 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6249. Min Range: -7.6249
Max Act: 6.8749. Min Act: -0.1700
Data Index: 5473568 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6249. Min Range: -7.6249
Max Act: 6.8437. Min Act: -0.1700
Data Index: 6278313 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6249. Min Range: -7.6249
Max Act: 6.8437. Min Act: -0.1700
Data Index: 2679999 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6249. Min Range: -7.6249
Max Act: 6.8437. Min Act: -0.1700
Data Index: 3443024 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6249. Min Range: -7.6249
Max Act: 6.8437. Min Act: -0.1700
Data Index: 3195786 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6249. Min Range: -7.6249
Max Act: 6.8437. Min Act: -0.1700
Data Index: 8143903 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6249. Min Range: -7.6249
Max Act: 6.8124. Min Act: -0.1700
Data Index: 8274617 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6249. Min Range: -7.6249
Max Act: 6.8124. Min Act: -0.1700
Data Index: 7047671 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19