Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4975 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7743. Min Range: -7.7743
Max Act: 7.7743. Min Act: -0.1700
Data Index: 2757665 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7743. Min Range: -7.7743
Max Act: 7.1181. Min Act: -0.1700
Data Index: 6609406 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7743. Min Range: -7.7743
Max Act: 7.1181. Min Act: -0.1700
Data Index: 4113727 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7743. Min Range: -7.7743
Max Act: 6.9931. Min Act: -0.1700
Data Index: 4616629 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7743. Min Range: -7.7743
Max Act: 6.9618. Min Act: -0.1700
Data Index: 6106517 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7743. Min Range: -7.7743
Max Act: 6.9306. Min Act: -0.1700
Data Index: 2551963 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7743. Min Range: -7.7743
Max Act: 6.9306. Min Act: -0.1700
Data Index: 8617405 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7743. Min Range: -7.7743
Max Act: 6.8056. Min Act: -0.1700
Data Index: 6225068 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7743. Min Range: -7.7743
Max Act: 6.7743. Min Act: -0.1700
Data Index: 411542 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7743. Min Range: -7.7743
Max Act: 6.7431. Min Act: -0.1700
Data Index: 3249548 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7743. Min Range: -7.7743
Max Act: 6.7431. Min Act: -0.1700
Data Index: 3656308 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7743. Min Range: -7.7743
Max Act: 6.7118. Min Act: -0.1700
Data Index: 6491547 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7743. Min Range: -7.7743
Max Act: 6.6806. Min Act: -0.1700
Data Index: 5173829 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7743. Min Range: -7.7743
Max Act: 6.6181. Min Act: -0.1700
Data Index: 63120 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7743. Min Range: -7.7743
Max Act: 6.6181. Min Act: -0.1700
Data Index: 3982395 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7743. Min Range: -7.7743
Max Act: 6.6181. Min Act: -0.1700
Data Index: 3587540 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7743. Min Range: -7.7743
Max Act: 6.6181. Min Act: -0.1700
Data Index: 209863 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7743. Min Range: -7.7743
Max Act: 6.5868. Min Act: -0.1700
Data Index: 4061706 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7743. Min Range: -7.7743
Max Act: 6.6181. Min Act: -0.1700
Data Index: 118655 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7743. Min Range: -7.7743
Max Act: 6.5868. Min Act: -0.1700
Data Index: 2621206 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #19