Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2565 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0836. Min Range: -4.0836
Max Act: 4.0836. Min Act: -0.1700
Data Index: 2276002 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0836. Min Range: -4.0836
Max Act: 3.8335. Min Act: -0.1700
Data Index: 6370704 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0836. Min Range: -4.0836
Max Act: 3.8022. Min Act: -0.1700
Data Index: 1034112 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0836. Min Range: -4.0836
Max Act: 3.8022. Min Act: -0.1700
Data Index: 1495452 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0836. Min Range: -4.0836
Max Act: 3.7709. Min Act: -0.1700
Data Index: 5025591 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0836. Min Range: -4.0836
Max Act: 3.7396. Min Act: -0.1700
Data Index: 8633767 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0836. Min Range: -4.0836
Max Act: 3.7553. Min Act: -0.1700
Data Index: 3226586 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0836. Min Range: -4.0836
Max Act: 3.7553. Min Act: -0.1700
Data Index: 3995241 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0836. Min Range: -4.0836
Max Act: 3.7553. Min Act: -0.1700
Data Index: 4372075 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0836. Min Range: -4.0836
Max Act: 3.7553. Min Act: -0.1700
Data Index: 7338327 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0836. Min Range: -4.0836
Max Act: 3.7396. Min Act: -0.1700
Data Index: 8051632 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0836. Min Range: -4.0836
Max Act: 3.7709. Min Act: -0.1700
Data Index: 572173 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0836. Min Range: -4.0836
Max Act: 3.6927. Min Act: -0.1700
Data Index: 7191048 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0836. Min Range: -4.0836
Max Act: 3.7084. Min Act: -0.1700
Data Index: 7710661 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0836. Min Range: -4.0836
Max Act: 3.6927. Min Act: -0.1700
Data Index: 8739385 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0836. Min Range: -4.0836
Max Act: 3.6927. Min Act: -0.1700
Data Index: 7228409 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0836. Min Range: -4.0836
Max Act: 3.7084. Min Act: -0.1700
Data Index: 5993917 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0836. Min Range: -4.0836
Max Act: 3.6614. Min Act: -0.1700
Data Index: 3720438 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0836. Min Range: -4.0836
Max Act: 3.6927. Min Act: -0.1700
Data Index: 1374696 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0836. Min Range: -4.0836
Max Act: 3.6771. Min Act: -0.1700
Data Index: 1386359 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #19