Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4815 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3785. Min Range: -5.3785
Max Act: 5.3785. Min Act: -0.1700
Data Index: 5037332 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3785. Min Range: -5.3785
Max Act: 5.2535. Min Act: -0.1700
Data Index: 1193087 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3785. Min Range: -5.3785
Max Act: 5.2222. Min Act: -0.1700
Data Index: 722179 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3785. Min Range: -5.3785
Max Act: 5.1597. Min Act: -0.1700
Data Index: 3318634 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3785. Min Range: -5.3785
Max Act: 5.1285. Min Act: -0.1700
Data Index: 4120109 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3785. Min Range: -5.3785
Max Act: 5.1285. Min Act: -0.1700
Data Index: 1039856 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3785. Min Range: -5.3785
Max Act: 5.1285. Min Act: -0.1700
Data Index: 7585977 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3785. Min Range: -5.3785
Max Act: 5.1285. Min Act: -0.1700
Data Index: 5561250 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3785. Min Range: -5.3785
Max Act: 5.0972. Min Act: -0.1700
Data Index: 8498643 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3785. Min Range: -5.3785
Max Act: 5.0972. Min Act: -0.1700
Data Index: 2619334 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3785. Min Range: -5.3785
Max Act: 5.0660. Min Act: -0.1700
Data Index: 1087264 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3785. Min Range: -5.3785
Max Act: 5.0660. Min Act: -0.1700
Data Index: 1631410 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3785. Min Range: -5.3785
Max Act: 5.0660. Min Act: -0.1700
Data Index: 1893417 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3785. Min Range: -5.3785
Max Act: 5.0347. Min Act: -0.1700
Data Index: 2790450 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3785. Min Range: -5.3785
Max Act: 5.0035. Min Act: -0.1700
Data Index: 4574174 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3785. Min Range: -5.3785
Max Act: 5.0347. Min Act: -0.1700
Data Index: 4729051 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3785. Min Range: -5.3785
Max Act: 5.0035. Min Act: -0.1700
Data Index: 6826599 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3785. Min Range: -5.3785
Max Act: 5.0035. Min Act: -0.1700
Data Index: 8339862 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3785. Min Range: -5.3785
Max Act: 4.9722. Min Act: -0.1700
Data Index: 4229899 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3785. Min Range: -5.3785
Max Act: 4.9722. Min Act: -0.1700
Data Index: 7076096 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #19