Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5023 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8881. Min Range: -3.8881
Max Act: 3.8881. Min Act: -0.1700
Data Index: 239988 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8881. Min Range: -3.8881
Max Act: 3.7630. Min Act: -0.1700
Data Index: 5164982 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8881. Min Range: -3.8881
Max Act: 3.7630. Min Act: -0.1700
Data Index: 3597983 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8881. Min Range: -3.8881
Max Act: 3.7474. Min Act: -0.1700
Data Index: 3223669 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8881. Min Range: -3.8881
Max Act: 3.7161. Min Act: -0.1700
Data Index: 6766389 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8881. Min Range: -3.8881
Max Act: 3.7005. Min Act: -0.1700
Data Index: 3327893 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8881. Min Range: -3.8881
Max Act: 3.6692. Min Act: -0.1700
Data Index: 7805281 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8881. Min Range: -3.8881
Max Act: 3.6379. Min Act: -0.1700
Data Index: 4778250 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8881. Min Range: -3.8881
Max Act: 3.6535. Min Act: -0.1700
Data Index: 2123484 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8881. Min Range: -3.8881
Max Act: 3.6379. Min Act: -0.1700
Data Index: 4942478 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8881. Min Range: -3.8881
Max Act: 3.6379. Min Act: -0.1700
Data Index: 7753313 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8881. Min Range: -3.8881
Max Act: 3.6379. Min Act: -0.1700
Data Index: 8398812 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8881. Min Range: -3.8881
Max Act: 3.6222. Min Act: -0.1700
Data Index: 4290815 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8881. Min Range: -3.8881
Max Act: 3.6066. Min Act: -0.1700
Data Index: 5761379 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8881. Min Range: -3.8881
Max Act: 3.5909. Min Act: -0.1700
Data Index: 7025299 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8881. Min Range: -3.8881
Max Act: 3.6066. Min Act: -0.1700
Data Index: 3029641 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8881. Min Range: -3.8881
Max Act: 3.5753. Min Act: -0.1700
Data Index: 2576052 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8881. Min Range: -3.8881
Max Act: 3.5753. Min Act: -0.1700
Data Index: 2370071 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8881. Min Range: -3.8881
Max Act: 3.5753. Min Act: -0.1700
Data Index: 578138 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8881. Min Range: -3.8881
Max Act: 3.5753. Min Act: -0.1700
Data Index: 3668931 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #19