Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1170 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.4574. Min Range: -1.4574
Max Act: 1.4574. Min Act: -0.1628
Data Index: 693497 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4574. Min Range: -1.4574
Max Act: 1.4398. Min Act: -0.1682
Data Index: 4816270 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4574. Min Range: -1.4574
Max Act: 1.4310. Min Act: -0.1662
Data Index: 2870197 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4574. Min Range: -1.4574
Max Act: 1.4222. Min Act: -0.1426
Data Index: 3513119 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4574. Min Range: -1.4574
Max Act: 1.4134. Min Act: -0.1667
Data Index: 8103772 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4574. Min Range: -1.4574
Max Act: 1.4222. Min Act: -0.1652
Data Index: 510173 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4574. Min Range: -1.4574
Max Act: 1.4134. Min Act: -0.1492
Data Index: 7549378 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4574. Min Range: -1.4574
Max Act: 1.4045. Min Act: -0.1696
Data Index: 6454190 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4574. Min Range: -1.4574
Max Act: 1.3869. Min Act: -0.1647
Data Index: 5268266 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4574. Min Range: -1.4574
Max Act: 1.4045. Min Act: -0.1700
Data Index: 7167449 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4574. Min Range: -1.4574
Max Act: 1.3781. Min Act: -0.1649
Data Index: 7027520 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4574. Min Range: -1.4574
Max Act: 1.3869. Min Act: -0.1532
Data Index: 4058500 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4574. Min Range: -1.4574
Max Act: 1.3781. Min Act: -0.1665
Data Index: 1363833 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4574. Min Range: -1.4574
Max Act: 1.3781. Min Act: -0.1671
Data Index: 8484297 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4574. Min Range: -1.4574
Max Act: 1.3781. Min Act: -0.1682
Data Index: 7680078 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4574. Min Range: -1.4574
Max Act: 1.3781. Min Act: -0.1624
Data Index: 7261904 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4574. Min Range: -1.4574
Max Act: 1.3781. Min Act: -0.1663
Data Index: 3089060 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4574. Min Range: -1.4574
Max Act: 1.3781. Min Act: -0.1621
Data Index: 4159906 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4574. Min Range: -1.4574
Max Act: 1.3781. Min Act: -0.1585
Data Index: 3424696 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4574. Min Range: -1.4574
Max Act: 1.3781. Min Act: -0.1589
Data Index: 2693684 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #19