Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6341 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3172. Min Range: -7.3172
Max Act: 7.3172. Min Act: -0.1700
Data Index: 722395 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3172. Min Range: -7.3172
Max Act: 7.1609. Min Act: -0.1700
Data Index: 8130566 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3172. Min Range: -7.3172
Max Act: 7.0672. Min Act: -0.1700
Data Index: 3615316 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3172. Min Range: -7.3172
Max Act: 7.0672. Min Act: -0.1700
Data Index: 1148032 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3172. Min Range: -7.3172
Max Act: 7.0047. Min Act: -0.1700
Data Index: 3070965 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3172. Min Range: -7.3172
Max Act: 6.9422. Min Act: -0.1700
Data Index: 256482 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3172. Min Range: -7.3172
Max Act: 6.8797. Min Act: -0.1700
Data Index: 2821418 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3172. Min Range: -7.3172
Max Act: 6.8797. Min Act: -0.1700
Data Index: 254246 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3172. Min Range: -7.3172
Max Act: 6.8797. Min Act: -0.1700
Data Index: 5426183 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3172. Min Range: -7.3172
Max Act: 6.8484. Min Act: -0.1700
Data Index: 7178876 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3172. Min Range: -7.3172
Max Act: 6.8172. Min Act: -0.1700
Data Index: 4772496 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3172. Min Range: -7.3172
Max Act: 6.8484. Min Act: -0.1700
Data Index: 6128290 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3172. Min Range: -7.3172
Max Act: 6.8172. Min Act: -0.1700
Data Index: 7953288 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3172. Min Range: -7.3172
Max Act: 6.8172. Min Act: -0.1700
Data Index: 7915375 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3172. Min Range: -7.3172
Max Act: 6.8172. Min Act: -0.1700
Data Index: 3621114 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3172. Min Range: -7.3172
Max Act: 6.7859. Min Act: -0.1700
Data Index: 4927671 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3172. Min Range: -7.3172
Max Act: 6.7859. Min Act: -0.1700
Data Index: 8601899 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3172. Min Range: -7.3172
Max Act: 6.7547. Min Act: -0.1700
Data Index: 4723640 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3172. Min Range: -7.3172
Max Act: 6.6922. Min Act: -0.1700
Data Index: 2998435 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3172. Min Range: -7.3172
Max Act: 6.6922. Min Act: -0.1700
Data Index: 4366274 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #19