Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2502 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1315. Min Range: -6.1315
Max Act: 6.1315. Min Act: -0.1700
Data Index: 5874545 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1315. Min Range: -6.1315
Max Act: 6.0377. Min Act: -0.1700
Data Index: 1690975 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1315. Min Range: -6.1315
Max Act: 6.0065. Min Act: -0.1700
Data Index: 7203240 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1315. Min Range: -6.1315
Max Act: 5.9752. Min Act: -0.1700
Data Index: 4547969 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1315. Min Range: -6.1315
Max Act: 5.8815. Min Act: -0.1700
Data Index: 2472377 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1315. Min Range: -6.1315
Max Act: 5.8815. Min Act: -0.1700
Data Index: 3418416 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1315. Min Range: -6.1315
Max Act: 5.8815. Min Act: -0.1700
Data Index: 6904267 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1315. Min Range: -6.1315
Max Act: 5.8190. Min Act: -0.1700
Data Index: 7886332 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1315. Min Range: -6.1315
Max Act: 5.8815. Min Act: -0.1700
Data Index: 2519879 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1315. Min Range: -6.1315
Max Act: 5.8502. Min Act: -0.1700
Data Index: 4709103 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1315. Min Range: -6.1315
Max Act: 5.7877. Min Act: -0.1700
Data Index: 4299403 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1315. Min Range: -6.1315
Max Act: 5.8190. Min Act: -0.1700
Data Index: 4235468 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1315. Min Range: -6.1315
Max Act: 5.8190. Min Act: -0.1700
Data Index: 3234932 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1315. Min Range: -6.1315
Max Act: 5.7877. Min Act: -0.1700
Data Index: 1481854 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1315. Min Range: -6.1315
Max Act: 5.8190. Min Act: -0.1700
Data Index: 1183777 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1315. Min Range: -6.1315
Max Act: 5.7877. Min Act: -0.1700
Data Index: 4515909 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1315. Min Range: -6.1315
Max Act: 5.7565. Min Act: -0.1700
Data Index: 797815 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1315. Min Range: -6.1315
Max Act: 5.7565. Min Act: -0.1700
Data Index: 1263659 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1315. Min Range: -6.1315
Max Act: 5.6940. Min Act: -0.1700
Data Index: 4140531 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1315. Min Range: -6.1315
Max Act: 5.6940. Min Act: -0.1700
Data Index: 5835427 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #19