Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 8 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9262. Min Range: -5.9262
Max Act: 5.9262. Min Act: -0.1700
Data Index: 222430 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9262. Min Range: -5.9262
Max Act: 5.6137. Min Act: -0.1700
Data Index: 2265620 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9262. Min Range: -5.9262
Max Act: 5.6137. Min Act: -0.1700
Data Index: 1352437 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9262. Min Range: -5.9262
Max Act: 5.5824. Min Act: -0.1700
Data Index: 7588880 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9262. Min Range: -5.9262
Max Act: 5.5512. Min Act: -0.1700
Data Index: 4439203 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9262. Min Range: -5.9262
Max Act: 5.5512. Min Act: -0.1700
Data Index: 522040 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9262. Min Range: -5.9262
Max Act: 5.5199. Min Act: -0.1700
Data Index: 7657519 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9262. Min Range: -5.9262
Max Act: 5.4887. Min Act: -0.1700
Data Index: 4409498 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9262. Min Range: -5.9262
Max Act: 5.4574. Min Act: -0.1700
Data Index: 7984296 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9262. Min Range: -5.9262
Max Act: 5.4574. Min Act: -0.1700
Data Index: 5454349 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9262. Min Range: -5.9262
Max Act: 5.4262. Min Act: -0.1700
Data Index: 7874992 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9262. Min Range: -5.9262
Max Act: 5.4262. Min Act: -0.1700
Data Index: 6845318 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9262. Min Range: -5.9262
Max Act: 5.3637. Min Act: -0.1700
Data Index: 7275818 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9262. Min Range: -5.9262
Max Act: 5.3949. Min Act: -0.1700
Data Index: 7102190 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9262. Min Range: -5.9262
Max Act: 5.3949. Min Act: -0.1700
Data Index: 1888897 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9262. Min Range: -5.9262
Max Act: 5.3637. Min Act: -0.1700
Data Index: 3256220 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9262. Min Range: -5.9262
Max Act: 5.3324. Min Act: -0.1700
Data Index: 2143429 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9262. Min Range: -5.9262
Max Act: 5.3324. Min Act: -0.1700
Data Index: 5855300 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9262. Min Range: -5.9262
Max Act: 5.3324. Min Act: -0.1700
Data Index: 2157319 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9262. Min Range: -5.9262
Max Act: 5.3012. Min Act: -0.1700
Data Index: 3521986 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #19