Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2673 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7424. Min Range: -2.7424
Max Act: 2.7424. Min Act: -0.1700
Data Index: 2463788 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7424. Min Range: -2.7424
Max Act: 2.7264. Min Act: -0.1700
Data Index: 5159091 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7424. Min Range: -2.7424
Max Act: 2.7104. Min Act: -0.1700
Data Index: 7213839 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7424. Min Range: -2.7424
Max Act: 2.7104. Min Act: -0.1700
Data Index: 1688529 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7424. Min Range: -2.7424
Max Act: 2.7104. Min Act: -0.1700
Data Index: 7952041 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7424. Min Range: -2.7424
Max Act: 2.6944. Min Act: -0.1700
Data Index: 6097939 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7424. Min Range: -2.7424
Max Act: 2.6944. Min Act: -0.1700
Data Index: 2385134 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7424. Min Range: -2.7424
Max Act: 2.6944. Min Act: -0.1700
Data Index: 4122841 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7424. Min Range: -2.7424
Max Act: 2.6944. Min Act: -0.1700
Data Index: 651874 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7424. Min Range: -2.7424
Max Act: 2.6944. Min Act: -0.1700
Data Index: 5915381 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7424. Min Range: -2.7424
Max Act: 2.6784. Min Act: -0.1700
Data Index: 3391460 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7424. Min Range: -2.7424
Max Act: 2.6784. Min Act: -0.1700
Data Index: 3995620 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7424. Min Range: -2.7424
Max Act: 2.6784. Min Act: -0.1700
Data Index: 38197 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7424. Min Range: -2.7424
Max Act: 2.6463. Min Act: -0.1700
Data Index: 3104883 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7424. Min Range: -2.7424
Max Act: 2.6624. Min Act: -0.1700
Data Index: 5069623 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7424. Min Range: -2.7424
Max Act: 2.6624. Min Act: -0.1700
Data Index: 1301797 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7424. Min Range: -2.7424
Max Act: 2.6624. Min Act: -0.1700
Data Index: 741545 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7424. Min Range: -2.7424
Max Act: 2.6624. Min Act: -0.1700
Data Index: 4949059 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7424. Min Range: -2.7424
Max Act: 2.6303. Min Act: -0.1700
Data Index: 945076 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7424. Min Range: -2.7424
Max Act: 2.6463. Min Act: -0.1700
Data Index: 647540 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #19