Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2826 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5338. Min Range: -6.5338
Max Act: 6.5338. Min Act: -0.1700
Data Index: 4381994 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5338. Min Range: -6.5338
Max Act: 6.3775. Min Act: -0.1700
Data Index: 4241222 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5338. Min Range: -6.5338
Max Act: 6.2838. Min Act: -0.1700
Data Index: 280735 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5338. Min Range: -6.5338
Max Act: 6.2213. Min Act: -0.1700
Data Index: 7833435 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5338. Min Range: -6.5338
Max Act: 6.1900. Min Act: -0.1700
Data Index: 3161652 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5338. Min Range: -6.5338
Max Act: 6.1900. Min Act: -0.1700
Data Index: 6213111 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5338. Min Range: -6.5338
Max Act: 6.1900. Min Act: -0.1700
Data Index: 3391764 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5338. Min Range: -6.5338
Max Act: 6.1275. Min Act: -0.1700
Data Index: 8688350 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5338. Min Range: -6.5338
Max Act: 6.0963. Min Act: -0.1700
Data Index: 4163893 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5338. Min Range: -6.5338
Max Act: 6.0650. Min Act: -0.1700
Data Index: 1649026 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5338. Min Range: -6.5338
Max Act: 6.0650. Min Act: -0.1700
Data Index: 2761116 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5338. Min Range: -6.5338
Max Act: 6.0650. Min Act: -0.1700
Data Index: 3434592 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5338. Min Range: -6.5338
Max Act: 6.0338. Min Act: -0.1700
Data Index: 3104000 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5338. Min Range: -6.5338
Max Act: 6.0025. Min Act: -0.1700
Data Index: 4148939 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5338. Min Range: -6.5338
Max Act: 6.0025. Min Act: -0.1700
Data Index: 678966 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5338. Min Range: -6.5338
Max Act: 5.9713. Min Act: -0.1700
Data Index: 3722123 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5338. Min Range: -6.5338
Max Act: 5.9713. Min Act: -0.1700
Data Index: 1696624 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5338. Min Range: -6.5338
Max Act: 5.9713. Min Act: -0.1700
Data Index: 2868266 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5338. Min Range: -6.5338
Max Act: 5.9400. Min Act: -0.1700
Data Index: 1256380 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5338. Min Range: -6.5338
Max Act: 5.9088. Min Act: -0.1700
Data Index: 6441132 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #19