Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3829 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2922. Min Range: -5.2922
Max Act: 5.2610. Min Act: -0.1700
Data Index: 7267251 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2922. Min Range: -5.2922
Max Act: 5.2922. Min Act: -0.1700
Data Index: 1576526 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2922. Min Range: -5.2922
Max Act: 5.1985. Min Act: -0.1700
Data Index: 2915273 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2922. Min Range: -5.2922
Max Act: 5.1672. Min Act: -0.1700
Data Index: 7120302 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2922. Min Range: -5.2922
Max Act: 5.1672. Min Act: -0.1700
Data Index: 7209720 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2922. Min Range: -5.2922
Max Act: 5.1047. Min Act: -0.1700
Data Index: 2552676 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2922. Min Range: -5.2922
Max Act: 5.1360. Min Act: -0.1700
Data Index: 3193227 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2922. Min Range: -5.2922
Max Act: 5.1360. Min Act: -0.1700
Data Index: 4091638 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2922. Min Range: -5.2922
Max Act: 5.0735. Min Act: -0.1700
Data Index: 7884211 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2922. Min Range: -5.2922
Max Act: 5.0735. Min Act: -0.1700
Data Index: 5971917 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2922. Min Range: -5.2922
Max Act: 5.1047. Min Act: -0.1700
Data Index: 2545115 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2922. Min Range: -5.2922
Max Act: 5.1360. Min Act: -0.1700
Data Index: 5502227 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2922. Min Range: -5.2922
Max Act: 5.1047. Min Act: -0.1700
Data Index: 7723424 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2922. Min Range: -5.2922
Max Act: 5.0735. Min Act: -0.1700
Data Index: 3899489 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2922. Min Range: -5.2922
Max Act: 5.0735. Min Act: -0.1700
Data Index: 1337622 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2922. Min Range: -5.2922
Max Act: 5.0735. Min Act: -0.1700
Data Index: 7934139 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2922. Min Range: -5.2922
Max Act: 5.0735. Min Act: -0.1700
Data Index: 5521245 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2922. Min Range: -5.2922
Max Act: 5.0735. Min Act: -0.1700
Data Index: 84785 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2922. Min Range: -5.2922
Max Act: 5.0735. Min Act: -0.1700
Data Index: 2003065 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2922. Min Range: -5.2922
Max Act: 5.0422. Min Act: -0.1700
Data Index: 746537 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #19