Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 733 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8564. Min Range: -5.8564
Max Act: 5.8564. Min Act: -0.1700
Data Index: 4526622 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8564. Min Range: -5.8564
Max Act: 5.8564. Min Act: -0.1700
Data Index: 5557064 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8564. Min Range: -5.8564
Max Act: 5.7939. Min Act: -0.1700
Data Index: 976071 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8564. Min Range: -5.8564
Max Act: 5.5439. Min Act: -0.1700
Data Index: 5236796 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8564. Min Range: -5.8564
Max Act: 5.5127. Min Act: -0.1700
Data Index: 6326706 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8564. Min Range: -5.8564
Max Act: 5.5127. Min Act: -0.1700
Data Index: 706161 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8564. Min Range: -5.8564
Max Act: 5.4814. Min Act: -0.1700
Data Index: 1924313 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8564. Min Range: -5.8564
Max Act: 5.4814. Min Act: -0.1700
Data Index: 271467 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8564. Min Range: -5.8564
Max Act: 5.4814. Min Act: -0.1700
Data Index: 271469 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8564. Min Range: -5.8564
Max Act: 5.4502. Min Act: -0.1700
Data Index: 5968468 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8564. Min Range: -5.8564
Max Act: 5.4189. Min Act: -0.1700
Data Index: 160946 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8564. Min Range: -5.8564
Max Act: 5.4502. Min Act: -0.1700
Data Index: 715554 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8564. Min Range: -5.8564
Max Act: 5.4189. Min Act: -0.1700
Data Index: 5516448 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8564. Min Range: -5.8564
Max Act: 5.3564. Min Act: -0.1700
Data Index: 7857799 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8564. Min Range: -5.8564
Max Act: 5.3877. Min Act: -0.1700
Data Index: 5514119 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8564. Min Range: -5.8564
Max Act: 5.3564. Min Act: -0.1700
Data Index: 3452559 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8564. Min Range: -5.8564
Max Act: 5.3252. Min Act: -0.1700
Data Index: 1005978 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8564. Min Range: -5.8564
Max Act: 5.3252. Min Act: -0.1700
Data Index: 4451217 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8564. Min Range: -5.8564
Max Act: 5.3252. Min Act: -0.1700
Data Index: 2825860 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8564. Min Range: -5.8564
Max Act: 5.3252. Min Act: -0.1700
Data Index: 4700385 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19