Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4077 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.5870. Min Range: -9.5870
Max Act: 9.5870. Min Act: -0.1700
Data Index: 6122492 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5870. Min Range: -9.5870
Max Act: 9.2745. Min Act: -0.1700
Data Index: 2640904 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5870. Min Range: -9.5870
Max Act: 9.2745. Min Act: -0.1700
Data Index: 71251 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5870. Min Range: -9.5870
Max Act: 9.2120. Min Act: -0.1700
Data Index: 1507438 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5870. Min Range: -9.5870
Max Act: 9.1495. Min Act: -0.1700
Data Index: 5604405 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5870. Min Range: -9.5870
Max Act: 9.1495. Min Act: -0.1700
Data Index: 3266382 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5870. Min Range: -9.5870
Max Act: 9.1495. Min Act: -0.1700
Data Index: 1275645 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5870. Min Range: -9.5870
Max Act: 9.2120. Min Act: -0.1700
Data Index: 5605381 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5870. Min Range: -9.5870
Max Act: 9.1495. Min Act: -0.1700
Data Index: 1209167 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5870. Min Range: -9.5870
Max Act: 9.1495. Min Act: -0.1700
Data Index: 23692 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5870. Min Range: -9.5870
Max Act: 9.0870. Min Act: -0.1700
Data Index: 5866971 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5870. Min Range: -9.5870
Max Act: 9.0245. Min Act: -0.1700
Data Index: 1181110 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5870. Min Range: -9.5870
Max Act: 9.0245. Min Act: -0.1700
Data Index: 8402611 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5870. Min Range: -9.5870
Max Act: 9.0245. Min Act: -0.1700
Data Index: 8184479 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5870. Min Range: -9.5870
Max Act: 9.0245. Min Act: -0.1700
Data Index: 884998 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5870. Min Range: -9.5870
Max Act: 9.0245. Min Act: -0.1700
Data Index: 4729709 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5870. Min Range: -9.5870
Max Act: 9.0245. Min Act: -0.1700
Data Index: 4551639 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5870. Min Range: -9.5870
Max Act: 9.0245. Min Act: -0.1700
Data Index: 6351840 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5870. Min Range: -9.5870
Max Act: 9.0870. Min Act: -0.1700
Data Index: 8548235 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5870. Min Range: -9.5870
Max Act: 9.0245. Min Act: -0.1700
Data Index: 4402559 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #19