Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2548 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5898. Min Range: -6.5898
Max Act: 6.5898. Min Act: -0.1700
Data Index: 4109466 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5898. Min Range: -6.5898
Max Act: 6.4023. Min Act: -0.1700
Data Index: 2016401 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5898. Min Range: -6.5898
Max Act: 6.2773. Min Act: -0.1700
Data Index: 3158708 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5898. Min Range: -6.5898
Max Act: 6.2773. Min Act: -0.1700
Data Index: 7927208 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5898. Min Range: -6.5898
Max Act: 6.2461. Min Act: -0.1700
Data Index: 3173108 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5898. Min Range: -6.5898
Max Act: 6.2461. Min Act: -0.1700
Data Index: 7992156 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5898. Min Range: -6.5898
Max Act: 6.2148. Min Act: -0.1700
Data Index: 4859181 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5898. Min Range: -6.5898
Max Act: 6.2148. Min Act: -0.1700
Data Index: 6091528 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5898. Min Range: -6.5898
Max Act: 6.2461. Min Act: -0.1700
Data Index: 218789 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5898. Min Range: -6.5898
Max Act: 6.1836. Min Act: -0.1700
Data Index: 7399143 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5898. Min Range: -6.5898
Max Act: 6.1523. Min Act: -0.1700
Data Index: 8391988 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5898. Min Range: -6.5898
Max Act: 6.1523. Min Act: -0.1700
Data Index: 5621794 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5898. Min Range: -6.5898
Max Act: 6.1523. Min Act: -0.1700
Data Index: 7972892 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5898. Min Range: -6.5898
Max Act: 6.1211. Min Act: -0.1700
Data Index: 7972891 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5898. Min Range: -6.5898
Max Act: 6.1211. Min Act: -0.1700
Data Index: 2365441 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5898. Min Range: -6.5898
Max Act: 6.1211. Min Act: -0.1700
Data Index: 6934519 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5898. Min Range: -6.5898
Max Act: 6.1211. Min Act: -0.1700
Data Index: 7244049 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5898. Min Range: -6.5898
Max Act: 6.0898. Min Act: -0.1700
Data Index: 1421822 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5898. Min Range: -6.5898
Max Act: 6.0898. Min Act: -0.1700
Data Index: 2070922 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5898. Min Range: -6.5898
Max Act: 6.0898. Min Act: -0.1700
Data Index: 2040765 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #19