Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2564 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8889. Min Range: -4.8889
Max Act: 4.8889. Min Act: -0.1700
Data Index: 326928 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8889. Min Range: -4.8889
Max Act: 4.8576. Min Act: -0.1700
Data Index: 196156 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8889. Min Range: -4.8889
Max Act: 4.8264. Min Act: -0.1700
Data Index: 4977776 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8889. Min Range: -4.8889
Max Act: 4.8264. Min Act: -0.1700
Data Index: 2440189 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8889. Min Range: -4.8889
Max Act: 4.8264. Min Act: -0.1700
Data Index: 2970104 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8889. Min Range: -4.8889
Max Act: 4.8264. Min Act: -0.1700
Data Index: 7988743 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8889. Min Range: -4.8889
Max Act: 4.7951. Min Act: -0.1700
Data Index: 647513 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8889. Min Range: -4.8889
Max Act: 4.7951. Min Act: -0.1700
Data Index: 6007851 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8889. Min Range: -4.8889
Max Act: 4.7951. Min Act: -0.1700
Data Index: 6144648 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8889. Min Range: -4.8889
Max Act: 4.7639. Min Act: -0.1700
Data Index: 4531218 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8889. Min Range: -4.8889
Max Act: 4.7326. Min Act: -0.1700
Data Index: 3688450 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8889. Min Range: -4.8889
Max Act: 4.7639. Min Act: -0.1700
Data Index: 5952824 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8889. Min Range: -4.8889
Max Act: 4.7326. Min Act: -0.1700
Data Index: 461397 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8889. Min Range: -4.8889
Max Act: 4.7639. Min Act: -0.1700
Data Index: 3842853 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8889. Min Range: -4.8889
Max Act: 4.7014. Min Act: -0.1700
Data Index: 6789454 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8889. Min Range: -4.8889
Max Act: 4.7639. Min Act: -0.1700
Data Index: 1286560 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8889. Min Range: -4.8889
Max Act: 4.7326. Min Act: -0.1700
Data Index: 1378039 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8889. Min Range: -4.8889
Max Act: 4.7326. Min Act: -0.1700
Data Index: 8205992 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8889. Min Range: -4.8889
Max Act: 4.7326. Min Act: -0.1700
Data Index: 8210978 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8889. Min Range: -4.8889
Max Act: 4.7014. Min Act: -0.1700
Data Index: 3497600 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #19