Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3761 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.0448. Min Range: -1.0448
Max Act: 1.0448. Min Act: -0.1700
Data Index: 491870 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0448. Min Range: -1.0448
Max Act: 1.0448. Min Act: -0.1700
Data Index: 2105293 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0448. Min Range: -1.0448
Max Act: 1.0361. Min Act: -0.1700
Data Index: 7348769 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0448. Min Range: -1.0448
Max Act: 1.0361. Min Act: -0.1700
Data Index: 3138383 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0448. Min Range: -1.0448
Max Act: 1.0448. Min Act: -0.1700
Data Index: 142898 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0448. Min Range: -1.0448
Max Act: 1.0274. Min Act: -0.1700
Data Index: 1016027 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0448. Min Range: -1.0448
Max Act: 1.0187. Min Act: -0.1700
Data Index: 8435787 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0448. Min Range: -1.0448
Max Act: 1.0187. Min Act: -0.1700
Data Index: 8169772 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0448. Min Range: -1.0448
Max Act: 1.0187. Min Act: -0.1700
Data Index: 7764417 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0448. Min Range: -1.0448
Max Act: 1.0187. Min Act: -0.1700
Data Index: 650215 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0448. Min Range: -1.0448
Max Act: 1.0100. Min Act: -0.1700
Data Index: 1820317 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0448. Min Range: -1.0448
Max Act: 1.0100. Min Act: -0.1700
Data Index: 8461794 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0448. Min Range: -1.0448
Max Act: 1.0100. Min Act: -0.1699
Data Index: 7747709 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0448. Min Range: -1.0448
Max Act: 1.0100. Min Act: -0.1700
Data Index: 7226477 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0448. Min Range: -1.0448
Max Act: 1.0187. Min Act: -0.1700
Data Index: 89356 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0448. Min Range: -1.0448
Max Act: 1.0187. Min Act: -0.1700
Data Index: 3909066 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0448. Min Range: -1.0448
Max Act: 1.0014. Min Act: -0.1700
Data Index: 2331393 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0448. Min Range: -1.0448
Max Act: 1.0014. Min Act: -0.1700
Data Index: 6776265 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0448. Min Range: -1.0448
Max Act: 0.9927. Min Act: -0.1700
Data Index: 684628 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0448. Min Range: -1.0448
Max Act: 1.0014. Min Act: -0.1700
Data Index: 8361331 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19