Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3467 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4768. Min Range: -3.4768
Max Act: 3.4768. Min Act: -0.1700
Data Index: 139441 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4768. Min Range: -3.4768
Max Act: 3.4455. Min Act: -0.1700
Data Index: 3153196 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4768. Min Range: -3.4768
Max Act: 3.4455. Min Act: -0.1700
Data Index: 5214546 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4768. Min Range: -3.4768
Max Act: 3.4455. Min Act: -0.1700
Data Index: 1852638 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4768. Min Range: -3.4768
Max Act: 3.4141. Min Act: -0.1700
Data Index: 1787946 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4768. Min Range: -3.4768
Max Act: 3.4141. Min Act: -0.1700
Data Index: 2014137 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4768. Min Range: -3.4768
Max Act: 3.4141. Min Act: -0.1700
Data Index: 2746613 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4768. Min Range: -3.4768
Max Act: 3.4141. Min Act: -0.1700
Data Index: 6357058 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4768. Min Range: -3.4768
Max Act: 3.4141. Min Act: -0.1700
Data Index: 7491264 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4768. Min Range: -3.4768
Max Act: 3.4141. Min Act: -0.1700
Data Index: 5043987 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4768. Min Range: -3.4768
Max Act: 3.3828. Min Act: -0.1700
Data Index: 3922757 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4768. Min Range: -3.4768
Max Act: 3.3828. Min Act: -0.1700
Data Index: 1215358 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4768. Min Range: -3.4768
Max Act: 3.3828. Min Act: -0.1700
Data Index: 3922756 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4768. Min Range: -3.4768
Max Act: 3.3828. Min Act: -0.1700
Data Index: 3730099 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4768. Min Range: -3.4768
Max Act: 3.3828. Min Act: -0.1700
Data Index: 1098962 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4768. Min Range: -3.4768
Max Act: 3.3828. Min Act: -0.1700
Data Index: 717381 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4768. Min Range: -3.4768
Max Act: 3.3828. Min Act: -0.1700
Data Index: 1042145 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4768. Min Range: -3.4768
Max Act: 3.3828. Min Act: -0.1700
Data Index: 3258278 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4768. Min Range: -3.4768
Max Act: 3.3828. Min Act: -0.1700
Data Index: 3153195 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4768. Min Range: -3.4768
Max Act: 3.3828. Min Act: -0.1700
Data Index: 908105 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19