Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 168 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.0537. Min Range: -1.0537
Max Act: 1.0537. Min Act: -0.1700
Data Index: 5102938 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0537. Min Range: -1.0537
Max Act: 0.9841. Min Act: -0.1700
Data Index: 5102936 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0537. Min Range: -1.0537
Max Act: 0.9323. Min Act: -0.1700
Data Index: 5102937 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0537. Min Range: -1.0537
Max Act: 0.9323. Min Act: -0.1700
Data Index: 1587238 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0537. Min Range: -1.0537
Max Act: 0.9237. Min Act: -0.1700
Data Index: 5102940 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0537. Min Range: -1.0537
Max Act: 0.9151. Min Act: -0.1700
Data Index: 6144376 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0537. Min Range: -1.0537
Max Act: 0.8895. Min Act: -0.1700
Data Index: 2234945 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0537. Min Range: -1.0537
Max Act: 0.8809. Min Act: -0.1700
Data Index: 2227486 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0537. Min Range: -1.0537
Max Act: 0.8809. Min Act: -0.1700
Data Index: 2058851 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0537. Min Range: -1.0537
Max Act: 0.8809. Min Act: -0.1700
Data Index: 2686054 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0537. Min Range: -1.0537
Max Act: 0.8639. Min Act: -0.1700
Data Index: 1676957 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0537. Min Range: -1.0537
Max Act: 0.8639. Min Act: -0.1700
Data Index: 1676953 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0537. Min Range: -1.0537
Max Act: 0.8639. Min Act: -0.1700
Data Index: 1676956 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0537. Min Range: -1.0537
Max Act: 0.8639. Min Act: -0.1700
Data Index: 1676959 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0537. Min Range: -1.0537
Max Act: 0.8639. Min Act: -0.1700
Data Index: 1676949 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0537. Min Range: -1.0537
Max Act: 0.8639. Min Act: -0.1700
Data Index: 1676958 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0537. Min Range: -1.0537
Max Act: 0.8639. Min Act: -0.1700
Data Index: 1676945 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0537. Min Range: -1.0537
Max Act: 0.8639. Min Act: -0.1700
Data Index: 1676967 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0537. Min Range: -1.0537
Max Act: 0.8639. Min Act: -0.1700
Data Index: 1676952 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0537. Min Range: -1.0537
Max Act: 0.8639. Min Act: -0.1700
Data Index: 1676947 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #19