Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 216 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4036. Min Range: -6.4036
Max Act: 6.4036. Min Act: -0.1700
Data Index: 79029 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4036. Min Range: -6.4036
Max Act: 6.3724. Min Act: -0.1700
Data Index: 505539 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4036. Min Range: -6.4036
Max Act: 6.3411. Min Act: -0.1700
Data Index: 5078955 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4036. Min Range: -6.4036
Max Act: 6.3099. Min Act: -0.1700
Data Index: 8684598 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4036. Min Range: -6.4036
Max Act: 6.2474. Min Act: -0.1700
Data Index: 5852085 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4036. Min Range: -6.4036
Max Act: 6.2474. Min Act: -0.1700
Data Index: 7550374 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4036. Min Range: -6.4036
Max Act: 6.1536. Min Act: -0.1700
Data Index: 7522843 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4036. Min Range: -6.4036
Max Act: 6.1224. Min Act: -0.1700
Data Index: 3412894 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4036. Min Range: -6.4036
Max Act: 6.0599. Min Act: -0.1700
Data Index: 6483368 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4036. Min Range: -6.4036
Max Act: 6.0911. Min Act: -0.1700
Data Index: 5521505 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4036. Min Range: -6.4036
Max Act: 6.0599. Min Act: -0.1700
Data Index: 7046779 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4036. Min Range: -6.4036
Max Act: 5.9974. Min Act: -0.1700
Data Index: 2340904 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4036. Min Range: -6.4036
Max Act: 5.9661. Min Act: -0.1700
Data Index: 2664088 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4036. Min Range: -6.4036
Max Act: 5.9974. Min Act: -0.1700
Data Index: 7063311 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4036. Min Range: -6.4036
Max Act: 5.9974. Min Act: -0.1700
Data Index: 4356540 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4036. Min Range: -6.4036
Max Act: 6.0286. Min Act: -0.1700
Data Index: 8448262 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4036. Min Range: -6.4036
Max Act: 5.9974. Min Act: -0.1700
Data Index: 6620630 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4036. Min Range: -6.4036
Max Act: 5.9661. Min Act: -0.1700
Data Index: 3610105 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4036. Min Range: -6.4036
Max Act: 5.9661. Min Act: -0.1700
Data Index: 4528295 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4036. Min Range: -6.4036
Max Act: 5.9349. Min Act: -0.1700
Data Index: 5581585 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #19