Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3783 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2492. Min Range: -7.2492
Max Act: 7.2492. Min Act: -0.1700
Data Index: 2173889 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2492. Min Range: -7.2492
Max Act: 7.1867. Min Act: -0.1700
Data Index: 8532507 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2492. Min Range: -7.2492
Max Act: 7.1242. Min Act: -0.1700
Data Index: 5196807 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2492. Min Range: -7.2492
Max Act: 7.0617. Min Act: -0.1700
Data Index: 2759919 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2492. Min Range: -7.2492
Max Act: 6.9680. Min Act: -0.1700
Data Index: 6238051 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2492. Min Range: -7.2492
Max Act: 6.9680. Min Act: -0.1700
Data Index: 997057 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2492. Min Range: -7.2492
Max Act: 6.8430. Min Act: -0.1700
Data Index: 3488534 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2492. Min Range: -7.2492
Max Act: 6.8117. Min Act: -0.1700
Data Index: 385221 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2492. Min Range: -7.2492
Max Act: 6.7805. Min Act: -0.1700
Data Index: 7965509 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2492. Min Range: -7.2492
Max Act: 6.7805. Min Act: -0.1700
Data Index: 5031438 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2492. Min Range: -7.2492
Max Act: 6.7805. Min Act: -0.1700
Data Index: 680824 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2492. Min Range: -7.2492
Max Act: 6.7492. Min Act: -0.1700
Data Index: 4689003 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2492. Min Range: -7.2492
Max Act: 6.7492. Min Act: -0.1700
Data Index: 4466105 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2492. Min Range: -7.2492
Max Act: 6.7180. Min Act: -0.1700
Data Index: 4651846 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2492. Min Range: -7.2492
Max Act: 6.6867. Min Act: -0.1700
Data Index: 8663053 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2492. Min Range: -7.2492
Max Act: 6.6867. Min Act: -0.1700
Data Index: 44499 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2492. Min Range: -7.2492
Max Act: 6.6555. Min Act: -0.1700
Data Index: 7693376 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2492. Min Range: -7.2492
Max Act: 6.6555. Min Act: -0.1700
Data Index: 3170224 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2492. Min Range: -7.2492
Max Act: 6.6242. Min Act: -0.1700
Data Index: 2923545 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2492. Min Range: -7.2492
Max Act: 6.5930. Min Act: -0.1700
Data Index: 7553608 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19