Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3012 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4313. Min Range: -4.4313
Max Act: 4.4313. Min Act: -0.1700
Data Index: 7456429 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4313. Min Range: -4.4313
Max Act: 4.3688. Min Act: -0.1700
Data Index: 7085369 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4313. Min Range: -4.4313
Max Act: 4.3688. Min Act: -0.1700
Data Index: 8150229 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4313. Min Range: -4.4313
Max Act: 4.3688. Min Act: -0.1700
Data Index: 5383184 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4313. Min Range: -4.4313
Max Act: 4.3375. Min Act: -0.1700
Data Index: 6004292 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4313. Min Range: -4.4313
Max Act: 4.2437. Min Act: -0.1700
Data Index: 4553854 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4313. Min Range: -4.4313
Max Act: 4.2750. Min Act: -0.1700
Data Index: 2843380 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4313. Min Range: -4.4313
Max Act: 4.2125. Min Act: -0.1700
Data Index: 5246779 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4313. Min Range: -4.4313
Max Act: 4.2437. Min Act: -0.1700
Data Index: 5544329 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4313. Min Range: -4.4313
Max Act: 4.1812. Min Act: -0.1700
Data Index: 8256207 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4313. Min Range: -4.4313
Max Act: 4.1812. Min Act: -0.1700
Data Index: 3386135 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4313. Min Range: -4.4313
Max Act: 4.1812. Min Act: -0.1700
Data Index: 6144739 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4313. Min Range: -4.4313
Max Act: 4.1812. Min Act: -0.1700
Data Index: 8033229 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4313. Min Range: -4.4313
Max Act: 4.1500. Min Act: -0.1700
Data Index: 6236195 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4313. Min Range: -4.4313
Max Act: 4.1187. Min Act: -0.1700
Data Index: 2267793 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4313. Min Range: -4.4313
Max Act: 4.1500. Min Act: -0.1700
Data Index: 1730567 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4313. Min Range: -4.4313
Max Act: 4.1187. Min Act: -0.1700
Data Index: 3464915 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4313. Min Range: -4.4313
Max Act: 4.0875. Min Act: -0.1700
Data Index: 5299901 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4313. Min Range: -4.4313
Max Act: 4.0875. Min Act: -0.1700
Data Index: 3935615 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4313. Min Range: -4.4313
Max Act: 4.0875. Min Act: -0.1700
Data Index: 2958258 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #19