Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1108 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9697. Min Range: -3.9697
Max Act: 3.9541. Min Act: -0.1700
Data Index: 2808888 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9697. Min Range: -3.9697
Max Act: 3.9697. Min Act: -0.1700
Data Index: 7266914 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9697. Min Range: -3.9697
Max Act: 3.9541. Min Act: -0.1700
Data Index: 6923304 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9697. Min Range: -3.9697
Max Act: 3.9072. Min Act: -0.1700
Data Index: 1578262 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9697. Min Range: -3.9697
Max Act: 3.9228. Min Act: -0.1700
Data Index: 5313387 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9697. Min Range: -3.9697
Max Act: 3.8759. Min Act: -0.1700
Data Index: 6096215 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9697. Min Range: -3.9697
Max Act: 3.9072. Min Act: -0.1700
Data Index: 136283 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9697. Min Range: -3.9697
Max Act: 3.8603. Min Act: -0.1700
Data Index: 6940510 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9697. Min Range: -3.9697
Max Act: 3.8603. Min Act: -0.1700
Data Index: 6046044 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9697. Min Range: -3.9697
Max Act: 3.8446. Min Act: -0.1700
Data Index: 5365838 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9697. Min Range: -3.9697
Max Act: 3.8759. Min Act: -0.1700
Data Index: 4623092 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9697. Min Range: -3.9697
Max Act: 3.8290. Min Act: -0.1700
Data Index: 6352706 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9697. Min Range: -3.9697
Max Act: 3.8290. Min Act: -0.1700
Data Index: 403629 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9697. Min Range: -3.9697
Max Act: 3.8446. Min Act: -0.1700
Data Index: 6626778 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9697. Min Range: -3.9697
Max Act: 3.8133. Min Act: -0.1700
Data Index: 5649014 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9697. Min Range: -3.9697
Max Act: 3.8290. Min Act: -0.1700
Data Index: 5789338 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9697. Min Range: -3.9697
Max Act: 3.7821. Min Act: -0.1700
Data Index: 1205428 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9697. Min Range: -3.9697
Max Act: 3.8133. Min Act: -0.1700
Data Index: 167362 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9697. Min Range: -3.9697
Max Act: 3.7977. Min Act: -0.1700
Data Index: 2001687 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9697. Min Range: -3.9697
Max Act: 3.7821. Min Act: -0.1700
Data Index: 3973546 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #19