Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2192 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9074. Min Range: -5.9074
Max Act: 5.9074. Min Act: -0.1700
Data Index: 3258735 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9074. Min Range: -5.9074
Max Act: 5.8762. Min Act: -0.1700
Data Index: 4529154 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9074. Min Range: -5.9074
Max Act: 5.7824. Min Act: -0.1700
Data Index: 3294895 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9074. Min Range: -5.9074
Max Act: 5.7824. Min Act: -0.1700
Data Index: 7689930 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9074. Min Range: -5.9074
Max Act: 5.7512. Min Act: -0.1700
Data Index: 5286627 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9074. Min Range: -5.9074
Max Act: 5.6887. Min Act: -0.1700
Data Index: 756472 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9074. Min Range: -5.9074
Max Act: 5.6574. Min Act: -0.1700
Data Index: 3559237 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9074. Min Range: -5.9074
Max Act: 5.5949. Min Act: -0.1700
Data Index: 2269471 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9074. Min Range: -5.9074
Max Act: 5.6262. Min Act: -0.1700
Data Index: 2509947 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9074. Min Range: -5.9074
Max Act: 5.5949. Min Act: -0.1700
Data Index: 5528779 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9074. Min Range: -5.9074
Max Act: 5.5949. Min Act: -0.1700
Data Index: 3092152 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9074. Min Range: -5.9074
Max Act: 5.5637. Min Act: -0.1700
Data Index: 7878675 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9074. Min Range: -5.9074
Max Act: 5.5637. Min Act: -0.1700
Data Index: 2045405 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9074. Min Range: -5.9074
Max Act: 5.5637. Min Act: -0.1700
Data Index: 7779863 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9074. Min Range: -5.9074
Max Act: 5.5637. Min Act: -0.1700
Data Index: 6102407 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9074. Min Range: -5.9074
Max Act: 5.5324. Min Act: -0.1700
Data Index: 647773 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9074. Min Range: -5.9074
Max Act: 5.5637. Min Act: -0.1700
Data Index: 7515183 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9074. Min Range: -5.9074
Max Act: 5.5324. Min Act: -0.1700
Data Index: 4803818 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9074. Min Range: -5.9074
Max Act: 5.5324. Min Act: -0.1700
Data Index: 718939 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9074. Min Range: -5.9074
Max Act: 5.5324. Min Act: -0.1700
Data Index: 3753939 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #19