Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5657 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8411. Min Range: -9.8411
Max Act: 9.8411. Min Act: -0.1700
Data Index: 7248571 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8411. Min Range: -9.8411
Max Act: 9.8411. Min Act: -0.1700
Data Index: 8466112 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8411. Min Range: -9.8411
Max Act: 9.7161. Min Act: -0.1700
Data Index: 2486691 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8411. Min Range: -9.8411
Max Act: 9.5911. Min Act: -0.1700
Data Index: 4988030 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8411. Min Range: -9.8411
Max Act: 9.5911. Min Act: -0.1700
Data Index: 4743922 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8411. Min Range: -9.8411
Max Act: 9.5286. Min Act: -0.1700
Data Index: 4433730 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8411. Min Range: -9.8411
Max Act: 9.4661. Min Act: -0.1700
Data Index: 602363 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8411. Min Range: -9.8411
Max Act: 9.4661. Min Act: -0.1700
Data Index: 5604922 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8411. Min Range: -9.8411
Max Act: 9.4036. Min Act: -0.1700
Data Index: 5513394 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8411. Min Range: -9.8411
Max Act: 9.4036. Min Act: -0.1700
Data Index: 6687095 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8411. Min Range: -9.8411
Max Act: 9.3411. Min Act: -0.1700
Data Index: 2484134 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8411. Min Range: -9.8411
Max Act: 9.3411. Min Act: -0.1700
Data Index: 5110912 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8411. Min Range: -9.8411
Max Act: 9.2161. Min Act: -0.1700
Data Index: 8692752 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8411. Min Range: -9.8411
Max Act: 9.2161. Min Act: -0.1700
Data Index: 6707471 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8411. Min Range: -9.8411
Max Act: 9.2161. Min Act: -0.1700
Data Index: 8572391 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8411. Min Range: -9.8411
Max Act: 9.2161. Min Act: -0.1700
Data Index: 344147 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8411. Min Range: -9.8411
Max Act: 9.2161. Min Act: -0.1700
Data Index: 8639352 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8411. Min Range: -9.8411
Max Act: 9.0911. Min Act: -0.1700
Data Index: 7413863 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8411. Min Range: -9.8411
Max Act: 9.0911. Min Act: -0.1700
Data Index: 3986810 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8411. Min Range: -9.8411
Max Act: 9.0286. Min Act: -0.1700
Data Index: 7558779 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #19