Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2691 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6541. Min Range: -7.6541
Max Act: 7.6541. Min Act: -0.1700
Data Index: 6449674 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6541. Min Range: -7.6541
Max Act: 7.5603. Min Act: -0.1700
Data Index: 2548378 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6541. Min Range: -7.6541
Max Act: 7.4041. Min Act: -0.1700
Data Index: 463843 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6541. Min Range: -7.6541
Max Act: 7.3103. Min Act: -0.1700
Data Index: 203743 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6541. Min Range: -7.6541
Max Act: 7.2478. Min Act: -0.1700
Data Index: 7670377 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6541. Min Range: -7.6541
Max Act: 7.2478. Min Act: -0.1700
Data Index: 1639898 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6541. Min Range: -7.6541
Max Act: 7.1853. Min Act: -0.1700
Data Index: 2343417 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6541. Min Range: -7.6541
Max Act: 7.1541. Min Act: -0.1700
Data Index: 5123206 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6541. Min Range: -7.6541
Max Act: 7.1228. Min Act: -0.1700
Data Index: 992230 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6541. Min Range: -7.6541
Max Act: 7.1228. Min Act: -0.1700
Data Index: 5346660 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6541. Min Range: -7.6541
Max Act: 7.1228. Min Act: -0.1700
Data Index: 4116061 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6541. Min Range: -7.6541
Max Act: 7.1228. Min Act: -0.1700
Data Index: 7577029 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6541. Min Range: -7.6541
Max Act: 7.1228. Min Act: -0.1700
Data Index: 5499254 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6541. Min Range: -7.6541
Max Act: 7.0916. Min Act: -0.1700
Data Index: 2256962 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6541. Min Range: -7.6541
Max Act: 7.0291. Min Act: -0.1700
Data Index: 6665963 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6541. Min Range: -7.6541
Max Act: 7.0291. Min Act: -0.1700
Data Index: 4184438 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6541. Min Range: -7.6541
Max Act: 7.0291. Min Act: -0.1700
Data Index: 152185 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6541. Min Range: -7.6541
Max Act: 7.0291. Min Act: -0.1700
Data Index: 3749358 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6541. Min Range: -7.6541
Max Act: 6.9978. Min Act: -0.1700
Data Index: 2070798 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6541. Min Range: -7.6541
Max Act: 6.9666. Min Act: -0.1700
Data Index: 2508107 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #19