Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3963 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7458. Min Range: -5.7458
Max Act: 5.7458. Min Act: -0.1700
Data Index: 1613297 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7458. Min Range: -5.7458
Max Act: 5.6208. Min Act: -0.1700
Data Index: 3650219 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7458. Min Range: -5.7458
Max Act: 5.5895. Min Act: -0.1700
Data Index: 1430685 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7458. Min Range: -5.7458
Max Act: 5.4645. Min Act: -0.1700
Data Index: 2528981 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7458. Min Range: -5.7458
Max Act: 5.4020. Min Act: -0.1700
Data Index: 3526792 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7458. Min Range: -5.7458
Max Act: 5.4020. Min Act: -0.1700
Data Index: 7000130 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7458. Min Range: -5.7458
Max Act: 5.3708. Min Act: -0.1700
Data Index: 29912 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7458. Min Range: -5.7458
Max Act: 5.3708. Min Act: -0.1700
Data Index: 4498099 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7458. Min Range: -5.7458
Max Act: 5.3395. Min Act: -0.1700
Data Index: 341714 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7458. Min Range: -5.7458
Max Act: 5.3083. Min Act: -0.1700
Data Index: 3940152 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7458. Min Range: -5.7458
Max Act: 5.3395. Min Act: -0.1700
Data Index: 8507050 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7458. Min Range: -5.7458
Max Act: 5.3395. Min Act: -0.1700
Data Index: 7085601 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7458. Min Range: -5.7458
Max Act: 5.3083. Min Act: -0.1700
Data Index: 7556033 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7458. Min Range: -5.7458
Max Act: 5.3083. Min Act: -0.1700
Data Index: 4276985 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7458. Min Range: -5.7458
Max Act: 5.3083. Min Act: -0.1700
Data Index: 386677 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7458. Min Range: -5.7458
Max Act: 5.2770. Min Act: -0.1700
Data Index: 122842 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7458. Min Range: -5.7458
Max Act: 5.2458. Min Act: -0.1700
Data Index: 8046678 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7458. Min Range: -5.7458
Max Act: 5.2458. Min Act: -0.1700
Data Index: 6262718 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7458. Min Range: -5.7458
Max Act: 5.2458. Min Act: -0.1700
Data Index: 3044751 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7458. Min Range: -5.7458
Max Act: 5.1833. Min Act: -0.1700
Data Index: 1313295 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #19