Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4828. Min Range: -4.4828
Max Act: 4.4828. Min Act: -0.1700
Data Index: 7392131 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4828. Min Range: -4.4828
Max Act: 4.4828. Min Act: -0.1700
Data Index: 229965 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4828. Min Range: -4.4828
Max Act: 4.4515. Min Act: -0.1700
Data Index: 3393546 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4828. Min Range: -4.4828
Max Act: 4.4203. Min Act: -0.1700
Data Index: 2486733 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4828. Min Range: -4.4828
Max Act: 4.3265. Min Act: -0.1700
Data Index: 1519545 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4828. Min Range: -4.4828
Max Act: 4.2953. Min Act: -0.1700
Data Index: 3243199 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4828. Min Range: -4.4828
Max Act: 4.2640. Min Act: -0.1700
Data Index: 4074608 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4828. Min Range: -4.4828
Max Act: 4.2640. Min Act: -0.1700
Data Index: 8289424 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4828. Min Range: -4.4828
Max Act: 4.2640. Min Act: -0.1700
Data Index: 746038 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4828. Min Range: -4.4828
Max Act: 4.2640. Min Act: -0.1700
Data Index: 4366933 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4828. Min Range: -4.4828
Max Act: 4.2015. Min Act: -0.1700
Data Index: 4823308 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4828. Min Range: -4.4828
Max Act: 4.2015. Min Act: -0.1700
Data Index: 3222125 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4828. Min Range: -4.4828
Max Act: 4.2015. Min Act: -0.1700
Data Index: 6168012 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4828. Min Range: -4.4828
Max Act: 4.1702. Min Act: -0.1700
Data Index: 5580726 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4828. Min Range: -4.4828
Max Act: 4.1702. Min Act: -0.1700
Data Index: 1463659 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4828. Min Range: -4.4828
Max Act: 4.2015. Min Act: -0.1700
Data Index: 3425102 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4828. Min Range: -4.4828
Max Act: 4.2015. Min Act: -0.1700
Data Index: 5200167 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4828. Min Range: -4.4828
Max Act: 4.1702. Min Act: -0.1700
Data Index: 3371071 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4828. Min Range: -4.4828
Max Act: 4.1702. Min Act: -0.1700
Data Index: 6798401 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4828. Min Range: -4.4828
Max Act: 4.1702. Min Act: -0.1700
Data Index: 7008027 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #19