Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4933 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7764. Min Range: -5.7764
Max Act: 5.7764. Min Act: -0.1700
Data Index: 2688016 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7764. Min Range: -5.7764
Max Act: 5.6514. Min Act: -0.1700
Data Index: 1893136 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7764. Min Range: -5.7764
Max Act: 5.6514. Min Act: -0.1700
Data Index: 8397738 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7764. Min Range: -5.7764
Max Act: 5.6514. Min Act: -0.1700
Data Index: 7580331 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7764. Min Range: -5.7764
Max Act: 5.6202. Min Act: -0.1700
Data Index: 3318987 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7764. Min Range: -5.7764
Max Act: 5.6202. Min Act: -0.1700
Data Index: 884687 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7764. Min Range: -5.7764
Max Act: 5.4952. Min Act: -0.1700
Data Index: 6051742 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7764. Min Range: -5.7764
Max Act: 5.4952. Min Act: -0.1700
Data Index: 4838600 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7764. Min Range: -5.7764
Max Act: 5.3702. Min Act: -0.1700
Data Index: 3599338 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7764. Min Range: -5.7764
Max Act: 5.3702. Min Act: -0.1700
Data Index: 4190385 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7764. Min Range: -5.7764
Max Act: 5.3702. Min Act: -0.1700
Data Index: 7671942 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7764. Min Range: -5.7764
Max Act: 5.3702. Min Act: -0.1700
Data Index: 1566742 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7764. Min Range: -5.7764
Max Act: 5.3702. Min Act: -0.1700
Data Index: 242767 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7764. Min Range: -5.7764
Max Act: 5.3389. Min Act: -0.1700
Data Index: 2951843 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7764. Min Range: -5.7764
Max Act: 5.3077. Min Act: -0.1700
Data Index: 7790565 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7764. Min Range: -5.7764
Max Act: 5.3077. Min Act: -0.1700
Data Index: 6746697 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7764. Min Range: -5.7764
Max Act: 5.3077. Min Act: -0.1700
Data Index: 6855826 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7764. Min Range: -5.7764
Max Act: 5.3077. Min Act: -0.1700
Data Index: 7242070 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7764. Min Range: -5.7764
Max Act: 5.3077. Min Act: -0.1700
Data Index: 1461697 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7764. Min Range: -5.7764
Max Act: 5.3077. Min Act: -0.1700
Data Index: 2933362 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19