Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4579 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1729. Min Range: -4.1729
Max Act: 4.1729. Min Act: -0.1700
Data Index: 806972 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1729. Min Range: -4.1729
Max Act: 4.1729. Min Act: -0.1700
Data Index: 6034780 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1729. Min Range: -4.1729
Max Act: 4.1104. Min Act: -0.1700
Data Index: 2265627 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1729. Min Range: -4.1729
Max Act: 4.0479. Min Act: -0.1700
Data Index: 1677504 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1729. Min Range: -4.1729
Max Act: 4.0166. Min Act: -0.1700
Data Index: 7049737 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1729. Min Range: -4.1729
Max Act: 4.0166. Min Act: -0.1700
Data Index: 4962216 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1729. Min Range: -4.1729
Max Act: 4.0166. Min Act: -0.1700
Data Index: 1794920 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1729. Min Range: -4.1729
Max Act: 3.9854. Min Act: -0.1700
Data Index: 1475882 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1729. Min Range: -4.1729
Max Act: 3.9854. Min Act: -0.1700
Data Index: 7712864 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1729. Min Range: -4.1729
Max Act: 3.9541. Min Act: -0.1700
Data Index: 6294063 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1729. Min Range: -4.1729
Max Act: 3.9228. Min Act: -0.1700
Data Index: 2804314 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1729. Min Range: -4.1729
Max Act: 3.9228. Min Act: -0.1700
Data Index: 1574283 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1729. Min Range: -4.1729
Max Act: 3.9228. Min Act: -0.1700
Data Index: 5745801 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1729. Min Range: -4.1729
Max Act: 3.9228. Min Act: -0.1700
Data Index: 2119684 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1729. Min Range: -4.1729
Max Act: 3.9228. Min Act: -0.1700
Data Index: 598038 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1729. Min Range: -4.1729
Max Act: 3.8916. Min Act: -0.1700
Data Index: 1803602 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1729. Min Range: -4.1729
Max Act: 3.8916. Min Act: -0.1700
Data Index: 4944088 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1729. Min Range: -4.1729
Max Act: 3.8916. Min Act: -0.1700
Data Index: 2800098 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1729. Min Range: -4.1729
Max Act: 3.8916. Min Act: -0.1700
Data Index: 2857257 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1729. Min Range: -4.1729
Max Act: 3.8916. Min Act: -0.1700
Data Index: 5701818 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #19