Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1174 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7955. Min Range: -5.7955
Max Act: 5.7955. Min Act: -0.1700
Data Index: 4681654 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7955. Min Range: -5.7955
Max Act: 5.7330. Min Act: -0.1700
Data Index: 3136092 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7955. Min Range: -5.7955
Max Act: 5.6705. Min Act: -0.1700
Data Index: 1051503 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7955. Min Range: -5.7955
Max Act: 5.6705. Min Act: -0.1700
Data Index: 5480202 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7955. Min Range: -5.7955
Max Act: 5.5455. Min Act: -0.1700
Data Index: 2275075 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7955. Min Range: -5.7955
Max Act: 5.5142. Min Act: -0.1700
Data Index: 5382116 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7955. Min Range: -5.7955
Max Act: 5.4517. Min Act: -0.1700
Data Index: 5666406 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7955. Min Range: -5.7955
Max Act: 5.4517. Min Act: -0.1700
Data Index: 5988855 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7955. Min Range: -5.7955
Max Act: 5.4517. Min Act: -0.1700
Data Index: 2108481 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7955. Min Range: -5.7955
Max Act: 5.4517. Min Act: -0.1700
Data Index: 861688 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7955. Min Range: -5.7955
Max Act: 5.4205. Min Act: -0.1700
Data Index: 5565864 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7955. Min Range: -5.7955
Max Act: 5.4205. Min Act: -0.1700
Data Index: 2147076 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7955. Min Range: -5.7955
Max Act: 5.3892. Min Act: -0.1700
Data Index: 167070 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7955. Min Range: -5.7955
Max Act: 5.3580. Min Act: -0.1700
Data Index: 4621107 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7955. Min Range: -5.7955
Max Act: 5.3580. Min Act: -0.1700
Data Index: 5214042 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7955. Min Range: -5.7955
Max Act: 5.3267. Min Act: -0.1700
Data Index: 3474559 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7955. Min Range: -5.7955
Max Act: 5.2955. Min Act: -0.1700
Data Index: 7832063 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7955. Min Range: -5.7955
Max Act: 5.3267. Min Act: -0.1700
Data Index: 6782177 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7955. Min Range: -5.7955
Max Act: 5.2955. Min Act: -0.1700
Data Index: 339715 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7955. Min Range: -5.7955
Max Act: 5.2955. Min Act: -0.1700
Data Index: 3381265 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #19