Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3483 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1167. Min Range: -7.1167
Max Act: 7.1167. Min Act: -0.1700
Data Index: 2424613 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1167. Min Range: -7.1167
Max Act: 7.0229. Min Act: -0.1700
Data Index: 2728523 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1167. Min Range: -7.1167
Max Act: 6.8667. Min Act: -0.1700
Data Index: 2990961 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1167. Min Range: -7.1167
Max Act: 6.8354. Min Act: -0.1700
Data Index: 3371443 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1167. Min Range: -7.1167
Max Act: 6.8042. Min Act: -0.1700
Data Index: 4380612 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1167. Min Range: -7.1167
Max Act: 6.7729. Min Act: -0.1700
Data Index: 6101386 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1167. Min Range: -7.1167
Max Act: 6.7729. Min Act: -0.1700
Data Index: 8547956 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1167. Min Range: -7.1167
Max Act: 6.7729. Min Act: -0.1700
Data Index: 3613158 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1167. Min Range: -7.1167
Max Act: 6.7417. Min Act: -0.1700
Data Index: 3058539 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1167. Min Range: -7.1167
Max Act: 6.7104. Min Act: -0.1700
Data Index: 6638214 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1167. Min Range: -7.1167
Max Act: 6.7104. Min Act: -0.1700
Data Index: 68961 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1167. Min Range: -7.1167
Max Act: 6.7104. Min Act: -0.1700
Data Index: 2069651 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1167. Min Range: -7.1167
Max Act: 6.7104. Min Act: -0.1700
Data Index: 5236901 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1167. Min Range: -7.1167
Max Act: 6.6792. Min Act: -0.1700
Data Index: 6104663 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1167. Min Range: -7.1167
Max Act: 6.6792. Min Act: -0.1700
Data Index: 3362492 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1167. Min Range: -7.1167
Max Act: 6.6792. Min Act: -0.1700
Data Index: 1609038 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1167. Min Range: -7.1167
Max Act: 6.6792. Min Act: -0.1700
Data Index: 8557870 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1167. Min Range: -7.1167
Max Act: 6.6479. Min Act: -0.1700
Data Index: 7595088 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1167. Min Range: -7.1167
Max Act: 6.6792. Min Act: -0.1700
Data Index: 312595 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1167. Min Range: -7.1167
Max Act: 6.6479. Min Act: -0.1700
Data Index: 8152814 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #19