Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4416 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8454. Min Range: -4.8454
Max Act: 4.8454. Min Act: -0.1700
Data Index: 4590709 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8454. Min Range: -4.8454
Max Act: 4.8141. Min Act: -0.1700
Data Index: 3762604 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8454. Min Range: -4.8454
Max Act: 4.7829. Min Act: -0.1700
Data Index: 431547 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8454. Min Range: -4.8454
Max Act: 4.6266. Min Act: -0.1700
Data Index: 3762603 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8454. Min Range: -4.8454
Max Act: 4.5954. Min Act: -0.1700
Data Index: 5084843 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8454. Min Range: -4.8454
Max Act: 4.5329. Min Act: -0.1700
Data Index: 7663880 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8454. Min Range: -4.8454
Max Act: 4.5329. Min Act: -0.1700
Data Index: 482583 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8454. Min Range: -4.8454
Max Act: 4.5016. Min Act: -0.1700
Data Index: 5946960 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8454. Min Range: -4.8454
Max Act: 4.5016. Min Act: -0.1700
Data Index: 6075508 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8454. Min Range: -4.8454
Max Act: 4.5016. Min Act: -0.1700
Data Index: 5895515 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8454. Min Range: -4.8454
Max Act: 4.4704. Min Act: -0.1700
Data Index: 6022408 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8454. Min Range: -4.8454
Max Act: 4.4391. Min Act: -0.1700
Data Index: 4187554 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8454. Min Range: -4.8454
Max Act: 4.4391. Min Act: -0.1700
Data Index: 3105504 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8454. Min Range: -4.8454
Max Act: 4.4704. Min Act: -0.1700
Data Index: 5778930 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8454. Min Range: -4.8454
Max Act: 4.4391. Min Act: -0.1700
Data Index: 5513089 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8454. Min Range: -4.8454
Max Act: 4.4704. Min Act: -0.1700
Data Index: 6345615 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8454. Min Range: -4.8454
Max Act: 4.4079. Min Act: -0.1700
Data Index: 3999893 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8454. Min Range: -4.8454
Max Act: 4.4079. Min Act: -0.1700
Data Index: 5788047 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8454. Min Range: -4.8454
Max Act: 4.3766. Min Act: -0.1700
Data Index: 4371684 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8454. Min Range: -4.8454
Max Act: 4.4079. Min Act: -0.1700
Data Index: 6693085 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #19