Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 697 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8243. Min Range: -6.8243
Max Act: 6.8243. Min Act: -0.1700
Data Index: 4801254 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8243. Min Range: -6.8243
Max Act: 6.7618. Min Act: -0.1700
Data Index: 7984971 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8243. Min Range: -6.8243
Max Act: 6.7305. Min Act: -0.1700
Data Index: 4402694 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8243. Min Range: -6.8243
Max Act: 6.6680. Min Act: -0.1700
Data Index: 2926262 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8243. Min Range: -6.8243
Max Act: 6.6680. Min Act: -0.1700
Data Index: 177898 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8243. Min Range: -6.8243
Max Act: 6.6368. Min Act: -0.1700
Data Index: 5799418 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8243. Min Range: -6.8243
Max Act: 6.6368. Min Act: -0.1700
Data Index: 1922559 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8243. Min Range: -6.8243
Max Act: 6.6055. Min Act: -0.1700
Data Index: 6627142 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8243. Min Range: -6.8243
Max Act: 6.5743. Min Act: -0.1700
Data Index: 6685487 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8243. Min Range: -6.8243
Max Act: 6.5118. Min Act: -0.1700
Data Index: 4884218 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8243. Min Range: -6.8243
Max Act: 6.5118. Min Act: -0.1700
Data Index: 5956328 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8243. Min Range: -6.8243
Max Act: 6.5118. Min Act: -0.1700
Data Index: 3139603 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8243. Min Range: -6.8243
Max Act: 6.4805. Min Act: -0.1700
Data Index: 6951517 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8243. Min Range: -6.8243
Max Act: 6.4805. Min Act: -0.1700
Data Index: 2084874 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8243. Min Range: -6.8243
Max Act: 6.4805. Min Act: -0.1700
Data Index: 1996411 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8243. Min Range: -6.8243
Max Act: 6.4493. Min Act: -0.1700
Data Index: 3849441 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8243. Min Range: -6.8243
Max Act: 6.4180. Min Act: -0.1700
Data Index: 2908309 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8243. Min Range: -6.8243
Max Act: 6.3868. Min Act: -0.1700
Data Index: 6132116 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8243. Min Range: -6.8243
Max Act: 6.3868. Min Act: -0.1700
Data Index: 6710797 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8243. Min Range: -6.8243
Max Act: 6.3868. Min Act: -0.1700
Data Index: 5360846 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19