Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3649 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1186. Min Range: -5.1186
Max Act: 5.1186. Min Act: -0.1700
Data Index: 7795700 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1186. Min Range: -5.1186
Max Act: 4.8061. Min Act: -0.1700
Data Index: 6392731 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1186. Min Range: -5.1186
Max Act: 4.7436. Min Act: -0.1700
Data Index: 2731352 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1186. Min Range: -5.1186
Max Act: 4.7124. Min Act: -0.1700
Data Index: 1075390 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1186. Min Range: -5.1186
Max Act: 4.7124. Min Act: -0.1700
Data Index: 1132629 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1186. Min Range: -5.1186
Max Act: 4.6499. Min Act: -0.1700
Data Index: 826979 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1186. Min Range: -5.1186
Max Act: 4.6499. Min Act: -0.1700
Data Index: 5979408 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1186. Min Range: -5.1186
Max Act: 4.6186. Min Act: -0.1700
Data Index: 3163215 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1186. Min Range: -5.1186
Max Act: 4.6186. Min Act: -0.1700
Data Index: 3611067 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1186. Min Range: -5.1186
Max Act: 4.5561. Min Act: -0.1700
Data Index: 2625841 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1186. Min Range: -5.1186
Max Act: 4.5561. Min Act: -0.1700
Data Index: 1608501 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1186. Min Range: -5.1186
Max Act: 4.5249. Min Act: -0.1700
Data Index: 3163212 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1186. Min Range: -5.1186
Max Act: 4.5249. Min Act: -0.1700
Data Index: 4318880 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1186. Min Range: -5.1186
Max Act: 4.4936. Min Act: -0.1700
Data Index: 5979403 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1186. Min Range: -5.1186
Max Act: 4.4936. Min Act: -0.1700
Data Index: 4044708 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1186. Min Range: -5.1186
Max Act: 4.4936. Min Act: -0.1700
Data Index: 5979412 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1186. Min Range: -5.1186
Max Act: 4.4936. Min Act: -0.1700
Data Index: 1501812 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1186. Min Range: -5.1186
Max Act: 4.4624. Min Act: -0.1700
Data Index: 8720514 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1186. Min Range: -5.1186
Max Act: 4.4936. Min Act: -0.1700
Data Index: 1722916 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1186. Min Range: -5.1186
Max Act: 4.4624. Min Act: -0.1700
Data Index: 4068873 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #19