Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1201 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.4313. Min Range: -10.4313
Max Act: 10.4313. Min Act: -0.1700
Data Index: 5822989 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4313. Min Range: -10.4313
Max Act: 10.0563. Min Act: -0.1700
Data Index: 3941730 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4313. Min Range: -10.4313
Max Act: 9.8063. Min Act: -0.1700
Data Index: 3243700 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4313. Min Range: -10.4313
Max Act: 9.6188. Min Act: -0.1700
Data Index: 6736746 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4313. Min Range: -10.4313
Max Act: 9.6188. Min Act: -0.1700
Data Index: 4435529 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4313. Min Range: -10.4313
Max Act: 9.6813. Min Act: -0.1700
Data Index: 5564146 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4313. Min Range: -10.4313
Max Act: 9.6188. Min Act: -0.1700
Data Index: 1265187 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4313. Min Range: -10.4313
Max Act: 9.6188. Min Act: -0.1700
Data Index: 1003959 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4313. Min Range: -10.4313
Max Act: 9.4938. Min Act: -0.1700
Data Index: 5581232 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4313. Min Range: -10.4313
Max Act: 9.4938. Min Act: -0.1700
Data Index: 623857 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4313. Min Range: -10.4313
Max Act: 9.4313. Min Act: -0.1700
Data Index: 6236442 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4313. Min Range: -10.4313
Max Act: 9.4938. Min Act: -0.1700
Data Index: 1042222 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4313. Min Range: -10.4313
Max Act: 9.4938. Min Act: -0.1700
Data Index: 1678184 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4313. Min Range: -10.4313
Max Act: 9.4938. Min Act: -0.1700
Data Index: 1767870 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4313. Min Range: -10.4313
Max Act: 9.4938. Min Act: -0.1700
Data Index: 5088629 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4313. Min Range: -10.4313
Max Act: 9.4938. Min Act: -0.1700
Data Index: 5208408 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4313. Min Range: -10.4313
Max Act: 9.5563. Min Act: -0.1700
Data Index: 1710491 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4313. Min Range: -10.4313
Max Act: 9.4938. Min Act: -0.1700
Data Index: 6575757 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4313. Min Range: -10.4313
Max Act: 9.3688. Min Act: -0.1700
Data Index: 1933952 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4313. Min Range: -10.4313
Max Act: 9.4938. Min Act: -0.1700
Data Index: 5502709 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #19