Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3268 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3869. Min Range: -4.3869
Max Act: 4.3869. Min Act: -0.1700
Data Index: 8789623 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3869. Min Range: -4.3869
Max Act: 4.2306. Min Act: -0.1700
Data Index: 1029577 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3869. Min Range: -4.3869
Max Act: 4.1994. Min Act: -0.1700
Data Index: 4435760 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3869. Min Range: -4.3869
Max Act: 4.2306. Min Act: -0.1700
Data Index: 3844972 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3869. Min Range: -4.3869
Max Act: 4.1994. Min Act: -0.1700
Data Index: 3124703 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3869. Min Range: -4.3869
Max Act: 4.1681. Min Act: -0.1700
Data Index: 1226141 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3869. Min Range: -4.3869
Max Act: 4.1681. Min Act: -0.1700
Data Index: 5365946 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3869. Min Range: -4.3869
Max Act: 4.1368. Min Act: -0.1700
Data Index: 2813336 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3869. Min Range: -4.3869
Max Act: 4.1681. Min Act: -0.1700
Data Index: 5107230 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3869. Min Range: -4.3869
Max Act: 4.1368. Min Act: -0.1700
Data Index: 3844971 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3869. Min Range: -4.3869
Max Act: 4.1681. Min Act: -0.1700
Data Index: 4726791 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3869. Min Range: -4.3869
Max Act: 4.1056. Min Act: -0.1700
Data Index: 2545104 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3869. Min Range: -4.3869
Max Act: 4.0743. Min Act: -0.1700
Data Index: 4448579 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3869. Min Range: -4.3869
Max Act: 4.0431. Min Act: -0.1700
Data Index: 405050 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3869. Min Range: -4.3869
Max Act: 4.0743. Min Act: -0.1700
Data Index: 2531794 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3869. Min Range: -4.3869
Max Act: 4.0743. Min Act: -0.1700
Data Index: 882206 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3869. Min Range: -4.3869
Max Act: 4.0431. Min Act: -0.1700
Data Index: 1027488 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3869. Min Range: -4.3869
Max Act: 4.0431. Min Act: -0.1700
Data Index: 6718309 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3869. Min Range: -4.3869
Max Act: 4.0118. Min Act: -0.1700
Data Index: 3767376 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3869. Min Range: -4.3869
Max Act: 4.0118. Min Act: -0.1700
Data Index: 5887685 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #19