Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2848 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6587. Min Range: -5.6587
Max Act: 5.6587. Min Act: -0.1700
Data Index: 4579144 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6587. Min Range: -5.6587
Max Act: 5.6275. Min Act: -0.1700
Data Index: 5394504 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6587. Min Range: -5.6587
Max Act: 5.5962. Min Act: -0.1700
Data Index: 7686626 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6587. Min Range: -5.6587
Max Act: 5.5962. Min Act: -0.1700
Data Index: 574138 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6587. Min Range: -5.6587
Max Act: 5.5962. Min Act: -0.1700
Data Index: 2100940 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6587. Min Range: -5.6587
Max Act: 5.6275. Min Act: -0.1700
Data Index: 879326 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6587. Min Range: -5.6587
Max Act: 5.5650. Min Act: -0.1700
Data Index: 317280 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6587. Min Range: -5.6587
Max Act: 5.5650. Min Act: -0.1700
Data Index: 8134729 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6587. Min Range: -5.6587
Max Act: 5.4712. Min Act: -0.1700
Data Index: 4703867 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6587. Min Range: -5.6587
Max Act: 5.4712. Min Act: -0.1700
Data Index: 5401690 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6587. Min Range: -5.6587
Max Act: 5.4400. Min Act: -0.1700
Data Index: 3984488 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6587. Min Range: -5.6587
Max Act: 5.4400. Min Act: -0.1700
Data Index: 5917545 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6587. Min Range: -5.6587
Max Act: 5.3462. Min Act: -0.1700
Data Index: 928484 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6587. Min Range: -5.6587
Max Act: 5.3775. Min Act: -0.1700
Data Index: 484986 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6587. Min Range: -5.6587
Max Act: 5.3462. Min Act: -0.1686
Data Index: 879330 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6587. Min Range: -5.6587
Max Act: 5.3775. Min Act: -0.1700
Data Index: 742765 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6587. Min Range: -5.6587
Max Act: 5.3775. Min Act: -0.1697
Data Index: 879329 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6587. Min Range: -5.6587
Max Act: 5.3462. Min Act: -0.1700
Data Index: 7223159 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6587. Min Range: -5.6587
Max Act: 5.3462. Min Act: -0.1700
Data Index: 430785 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6587. Min Range: -5.6587
Max Act: 5.3462. Min Act: -0.1700
Data Index: 1623143 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #19