Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1522 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7228. Min Range: -2.7228
Max Act: 2.7228. Min Act: -0.1700
Data Index: 256539 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7228. Min Range: -2.7228
Max Act: 2.6908. Min Act: -0.1700
Data Index: 2844951 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7228. Min Range: -2.7228
Max Act: 2.6747. Min Act: -0.1700
Data Index: 3784965 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7228. Min Range: -2.7228
Max Act: 2.7068. Min Act: -0.1700
Data Index: 7096612 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7228. Min Range: -2.7228
Max Act: 2.6747. Min Act: -0.1700
Data Index: 909326 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7228. Min Range: -2.7228
Max Act: 2.6587. Min Act: -0.1700
Data Index: 5215644 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7228. Min Range: -2.7228
Max Act: 2.6587. Min Act: -0.1700
Data Index: 2025941 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7228. Min Range: -2.7228
Max Act: 2.6266. Min Act: -0.1700
Data Index: 7892336 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7228. Min Range: -2.7228
Max Act: 2.6427. Min Act: -0.1700
Data Index: 951423 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7228. Min Range: -2.7228
Max Act: 2.5944. Min Act: -0.1700
Data Index: 4854768 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7228. Min Range: -2.7228
Max Act: 2.6105. Min Act: -0.1700
Data Index: 6014829 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7228. Min Range: -2.7228
Max Act: 2.5944. Min Act: -0.1700
Data Index: 829750 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7228. Min Range: -2.7228
Max Act: 2.5783. Min Act: -0.1700
Data Index: 6063825 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7228. Min Range: -2.7228
Max Act: 2.5944. Min Act: -0.1700
Data Index: 6063824 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7228. Min Range: -2.7228
Max Act: 2.5783. Min Act: -0.1700
Data Index: 73243 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7228. Min Range: -2.7228
Max Act: 2.5783. Min Act: -0.1700
Data Index: 2420396 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7228. Min Range: -2.7228
Max Act: 2.5783. Min Act: -0.1700
Data Index: 7701967 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7228. Min Range: -2.7228
Max Act: 2.5944. Min Act: -0.1700
Data Index: 6694609 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7228. Min Range: -2.7228
Max Act: 2.5783. Min Act: -0.1700
Data Index: 1676566 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7228. Min Range: -2.7228
Max Act: 2.5783. Min Act: -0.1700
Data Index: 6451935 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19