Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2867 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6759. Min Range: -6.6759
Max Act: 6.6759. Min Act: -0.1700
Data Index: 3162695 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6759. Min Range: -6.6759
Max Act: 6.6447. Min Act: -0.1700
Data Index: 8545139 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6759. Min Range: -6.6759
Max Act: 6.6134. Min Act: -0.1700
Data Index: 1187794 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6759. Min Range: -6.6759
Max Act: 6.5509. Min Act: -0.1700
Data Index: 867960 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6759. Min Range: -6.6759
Max Act: 6.5509. Min Act: -0.1700
Data Index: 5468499 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6759. Min Range: -6.6759
Max Act: 6.5822. Min Act: -0.1700
Data Index: 1419167 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6759. Min Range: -6.6759
Max Act: 6.5509. Min Act: -0.1700
Data Index: 6435756 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6759. Min Range: -6.6759
Max Act: 6.4884. Min Act: -0.1700
Data Index: 6706282 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6759. Min Range: -6.6759
Max Act: 6.5197. Min Act: -0.1700
Data Index: 398891 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6759. Min Range: -6.6759
Max Act: 6.4572. Min Act: -0.1700
Data Index: 8552370 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6759. Min Range: -6.6759
Max Act: 6.3947. Min Act: -0.1700
Data Index: 8200957 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6759. Min Range: -6.6759
Max Act: 6.3947. Min Act: -0.1700
Data Index: 1931151 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6759. Min Range: -6.6759
Max Act: 6.3947. Min Act: -0.1700
Data Index: 1223344 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6759. Min Range: -6.6759
Max Act: 6.3634. Min Act: -0.1700
Data Index: 192211 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6759. Min Range: -6.6759
Max Act: 6.3634. Min Act: -0.1700
Data Index: 3533458 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6759. Min Range: -6.6759
Max Act: 6.3947. Min Act: -0.1700
Data Index: 6893493 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6759. Min Range: -6.6759
Max Act: 6.3322. Min Act: -0.1700
Data Index: 7676422 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6759. Min Range: -6.6759
Max Act: 6.3322. Min Act: -0.1700
Data Index: 6996249 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6759. Min Range: -6.6759
Max Act: 6.3322. Min Act: -0.1700
Data Index: 4009951 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6759. Min Range: -6.6759
Max Act: 6.3322. Min Act: -0.1700
Data Index: 5918120 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #19