Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5616 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6683. Min Range: -5.6683
Max Act: 5.6683. Min Act: -0.1700
Data Index: 2914917 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6683. Min Range: -5.6683
Max Act: 5.3558. Min Act: -0.1699
Data Index: 8754193 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6683. Min Range: -5.6683
Max Act: 5.3558. Min Act: -0.1700
Data Index: 7400471 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6683. Min Range: -5.6683
Max Act: 5.2933. Min Act: -0.1700
Data Index: 4983222 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6683. Min Range: -5.6683
Max Act: 5.3246. Min Act: -0.1700
Data Index: 8251660 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6683. Min Range: -5.6683
Max Act: 5.3246. Min Act: -0.1700
Data Index: 2157836 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6683. Min Range: -5.6683
Max Act: 5.3246. Min Act: -0.1700
Data Index: 7818558 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6683. Min Range: -5.6683
Max Act: 5.3246. Min Act: -0.1700
Data Index: 5480079 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6683. Min Range: -5.6683
Max Act: 5.2933. Min Act: -0.1700
Data Index: 2467058 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6683. Min Range: -5.6683
Max Act: 5.2933. Min Act: -0.1700
Data Index: 2581815 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6683. Min Range: -5.6683
Max Act: 5.2933. Min Act: -0.1700
Data Index: 4049596 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6683. Min Range: -5.6683
Max Act: 5.2933. Min Act: -0.1700
Data Index: 5151389 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6683. Min Range: -5.6683
Max Act: 5.2933. Min Act: -0.1700
Data Index: 8222064 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6683. Min Range: -5.6683
Max Act: 5.2308. Min Act: -0.1700
Data Index: 5614718 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6683. Min Range: -5.6683
Max Act: 5.2621. Min Act: -0.1698
Data Index: 8241829 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6683. Min Range: -5.6683
Max Act: 5.2308. Min Act: -0.1700
Data Index: 8241805 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6683. Min Range: -5.6683
Max Act: 5.2308. Min Act: -0.1700
Data Index: 4322627 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6683. Min Range: -5.6683
Max Act: 5.2308. Min Act: -0.1700
Data Index: 2841034 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6683. Min Range: -5.6683
Max Act: 5.2308. Min Act: -0.1700
Data Index: 6627443 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6683. Min Range: -5.6683
Max Act: 5.1996. Min Act: -0.1700
Data Index: 3359164 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #19