Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4043 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4895. Min Range: -4.4895
Max Act: 4.4895. Min Act: -0.1700
Data Index: 6178130 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4895. Min Range: -4.4895
Max Act: 4.4270. Min Act: -0.1700
Data Index: 5426650 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4895. Min Range: -4.4895
Max Act: 4.3332. Min Act: -0.1700
Data Index: 6273085 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4895. Min Range: -4.4895
Max Act: 4.3019. Min Act: -0.1700
Data Index: 458240 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4895. Min Range: -4.4895
Max Act: 4.3019. Min Act: -0.1699
Data Index: 495515 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4895. Min Range: -4.4895
Max Act: 4.3019. Min Act: -0.1699
Data Index: 4616769 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4895. Min Range: -4.4895
Max Act: 4.2707. Min Act: -0.1700
Data Index: 6918902 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4895. Min Range: -4.4895
Max Act: 4.2394. Min Act: -0.1700
Data Index: 3771608 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4895. Min Range: -4.4895
Max Act: 4.2394. Min Act: -0.1700
Data Index: 6520671 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4895. Min Range: -4.4895
Max Act: 4.2082. Min Act: -0.1699
Data Index: 253565 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4895. Min Range: -4.4895
Max Act: 4.2707. Min Act: -0.1700
Data Index: 2540314 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4895. Min Range: -4.4895
Max Act: 4.2082. Min Act: -0.1698
Data Index: 5478682 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4895. Min Range: -4.4895
Max Act: 4.1769. Min Act: -0.1700
Data Index: 5544746 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4895. Min Range: -4.4895
Max Act: 4.2082. Min Act: -0.1700
Data Index: 7843839 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4895. Min Range: -4.4895
Max Act: 4.1769. Min Act: -0.1700
Data Index: 3479194 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4895. Min Range: -4.4895
Max Act: 4.1457. Min Act: -0.1700
Data Index: 5290168 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4895. Min Range: -4.4895
Max Act: 4.1769. Min Act: -0.1700
Data Index: 5268078 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4895. Min Range: -4.4895
Max Act: 4.1144. Min Act: -0.1700
Data Index: 1566782 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4895. Min Range: -4.4895
Max Act: 4.1769. Min Act: -0.1698
Data Index: 2860160 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4895. Min Range: -4.4895
Max Act: 4.2082. Min Act: -0.1700
Data Index: 3694635 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #19