Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5508 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1368. Min Range: -4.1368
Max Act: 4.1368. Min Act: -0.1700
Data Index: 8188082 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1368. Min Range: -4.1368
Max Act: 4.1055. Min Act: -0.1700
Data Index: 4690496 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1368. Min Range: -4.1368
Max Act: 4.0430. Min Act: -0.1700
Data Index: 454533 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1368. Min Range: -4.1368
Max Act: 4.0117. Min Act: -0.1700
Data Index: 887547 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1368. Min Range: -4.1368
Max Act: 3.9805. Min Act: -0.1700
Data Index: 5483968 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1368. Min Range: -4.1368
Max Act: 3.9492. Min Act: -0.1700
Data Index: 3970834 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1368. Min Range: -4.1368
Max Act: 3.9179. Min Act: -0.1700
Data Index: 2267273 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1368. Min Range: -4.1368
Max Act: 3.9179. Min Act: -0.1700
Data Index: 458237 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1368. Min Range: -4.1368
Max Act: 3.9179. Min Act: -0.1700
Data Index: 557110 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1368. Min Range: -4.1368
Max Act: 3.8867. Min Act: -0.1700
Data Index: 1471664 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1368. Min Range: -4.1368
Max Act: 3.8867. Min Act: -0.1700
Data Index: 7650 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1368. Min Range: -4.1368
Max Act: 3.8867. Min Act: -0.1700
Data Index: 153060 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1368. Min Range: -4.1368
Max Act: 3.8867. Min Act: -0.1700
Data Index: 6777754 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1368. Min Range: -4.1368
Max Act: 3.8554. Min Act: -0.1700
Data Index: 1688842 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1368. Min Range: -4.1368
Max Act: 3.8554. Min Act: -0.1700
Data Index: 7401696 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1368. Min Range: -4.1368
Max Act: 3.8867. Min Act: -0.1700
Data Index: 3698690 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1368. Min Range: -4.1368
Max Act: 3.8554. Min Act: -0.1700
Data Index: 2013728 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1368. Min Range: -4.1368
Max Act: 3.8554. Min Act: -0.1700
Data Index: 4460026 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1368. Min Range: -4.1368
Max Act: 3.8554. Min Act: -0.1700
Data Index: 1233878 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1368. Min Range: -4.1368
Max Act: 3.8554. Min Act: -0.1700
Data Index: 2519632 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19