Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5505 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1904. Min Range: -6.1904
Max Act: 6.1904. Min Act: -0.1700
Data Index: 4836012 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1904. Min Range: -6.1904
Max Act: 5.9092. Min Act: -0.1700
Data Index: 5544943 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1904. Min Range: -6.1904
Max Act: 5.7529. Min Act: -0.1700
Data Index: 2487029 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1904. Min Range: -6.1904
Max Act: 5.6592. Min Act: -0.1700
Data Index: 7690877 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1904. Min Range: -6.1904
Max Act: 5.6904. Min Act: -0.1700
Data Index: 7754425 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1904. Min Range: -6.1904
Max Act: 5.6279. Min Act: -0.1700
Data Index: 623315 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1904. Min Range: -6.1904
Max Act: 5.6592. Min Act: -0.1700
Data Index: 5252392 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1904. Min Range: -6.1904
Max Act: 5.6279. Min Act: -0.1700
Data Index: 4188442 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1904. Min Range: -6.1904
Max Act: 5.5967. Min Act: -0.1700
Data Index: 5926707 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1904. Min Range: -6.1904
Max Act: 5.5967. Min Act: -0.1700
Data Index: 8766673 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1904. Min Range: -6.1904
Max Act: 5.5967. Min Act: -0.1700
Data Index: 6415496 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1904. Min Range: -6.1904
Max Act: 5.5654. Min Act: -0.1700
Data Index: 3043851 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1904. Min Range: -6.1904
Max Act: 5.5967. Min Act: -0.1700
Data Index: 5795882 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1904. Min Range: -6.1904
Max Act: 5.5654. Min Act: -0.1700
Data Index: 5955042 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1904. Min Range: -6.1904
Max Act: 5.5654. Min Act: -0.1700
Data Index: 3558179 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1904. Min Range: -6.1904
Max Act: 5.5342. Min Act: -0.1700
Data Index: 2470311 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1904. Min Range: -6.1904
Max Act: 5.5029. Min Act: -0.1700
Data Index: 1796183 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1904. Min Range: -6.1904
Max Act: 5.4717. Min Act: -0.1700
Data Index: 5028293 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1904. Min Range: -6.1904
Max Act: 5.4717. Min Act: -0.1700
Data Index: 5693649 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1904. Min Range: -6.1904
Max Act: 5.5029. Min Act: -0.1700
Data Index: 647844 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19