Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1996 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.5857. Min Act: -0.1700
Data Index: 8563485 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.5545. Min Act: -0.1700
Data Index: 1157138 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.4295. Min Act: -0.1700
Data Index: 8675536 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.3670. Min Act: -0.1700
Data Index: 2896748 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.3670. Min Act: -0.1700
Data Index: 3348867 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.2732. Min Act: -0.1700
Data Index: 6370358 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.2420. Min Act: -0.1700
Data Index: 1494443 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.2107. Min Act: -0.1700
Data Index: 480158 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.1795. Min Act: -0.1700
Data Index: 4876225 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.1795. Min Act: -0.1700
Data Index: 4767634 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.1795. Min Act: -0.1700
Data Index: 3045553 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.1795. Min Act: -0.1700
Data Index: 6922952 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.1795. Min Act: -0.1700
Data Index: 1907949 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.1482. Min Act: -0.1700
Data Index: 7895791 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.1482. Min Act: -0.1700
Data Index: 170418 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.1482. Min Act: -0.1700
Data Index: 7951822 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.1170. Min Act: -0.1700
Data Index: 6892405 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.1170. Min Act: -0.1700
Data Index: 6527699 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.1170. Min Act: -0.1700
Data Index: 4281729 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.1170. Min Act: -0.1700
Data Index: 8361937 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #19