Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4996 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6698. Min Range: -6.6698
Max Act: 6.6698. Min Act: -0.1700
Data Index: 6013133 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6698. Min Range: -6.6698
Max Act: 6.6073. Min Act: -0.1700
Data Index: 5359388 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6698. Min Range: -6.6698
Max Act: 6.5448. Min Act: -0.1700
Data Index: 1058086 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6698. Min Range: -6.6698
Max Act: 6.5135. Min Act: -0.1700
Data Index: 8011568 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6698. Min Range: -6.6698
Max Act: 6.5135. Min Act: -0.1700
Data Index: 3281780 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6698. Min Range: -6.6698
Max Act: 6.5135. Min Act: -0.1700
Data Index: 4155895 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6698. Min Range: -6.6698
Max Act: 6.4510. Min Act: -0.1700
Data Index: 4129326 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6698. Min Range: -6.6698
Max Act: 6.4198. Min Act: -0.1700
Data Index: 3323210 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6698. Min Range: -6.6698
Max Act: 6.4198. Min Act: -0.1700
Data Index: 4129332 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6698. Min Range: -6.6698
Max Act: 6.4198. Min Act: -0.1700
Data Index: 3151756 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6698. Min Range: -6.6698
Max Act: 6.4510. Min Act: -0.1700
Data Index: 7693954 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6698. Min Range: -6.6698
Max Act: 6.3885. Min Act: -0.1700
Data Index: 2900562 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6698. Min Range: -6.6698
Max Act: 6.3885. Min Act: -0.1700
Data Index: 7752888 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6698. Min Range: -6.6698
Max Act: 6.3885. Min Act: -0.1700
Data Index: 308330 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6698. Min Range: -6.6698
Max Act: 6.3573. Min Act: -0.1700
Data Index: 8231573 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6698. Min Range: -6.6698
Max Act: 6.3573. Min Act: -0.1700
Data Index: 321340 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6698. Min Range: -6.6698
Max Act: 6.3573. Min Act: -0.1700
Data Index: 3752392 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6698. Min Range: -6.6698
Max Act: 6.3573. Min Act: -0.1700
Data Index: 1454466 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6698. Min Range: -6.6698
Max Act: 6.3260. Min Act: -0.1700
Data Index: 308329 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6698. Min Range: -6.6698
Max Act: 6.3260. Min Act: -0.1700
Data Index: 297843 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19