Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 481 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0751. Min Range: -3.0751
Max Act: 3.0751. Min Act: -0.1700
Data Index: 3598425 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0751. Min Range: -3.0751
Max Act: 3.0594. Min Act: -0.1700
Data Index: 6909028 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0751. Min Range: -3.0751
Max Act: 3.0278. Min Act: -0.1700
Data Index: 6191714 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0751. Min Range: -3.0751
Max Act: 2.9646. Min Act: -0.1700
Data Index: 8110637 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0751. Min Range: -3.0751
Max Act: 2.9646. Min Act: -0.1700
Data Index: 108747 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0751. Min Range: -3.0751
Max Act: 2.9646. Min Act: -0.1698
Data Index: 2889740 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0751. Min Range: -3.0751
Max Act: 2.9487. Min Act: -0.1700
Data Index: 1159479 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0751. Min Range: -3.0751
Max Act: 2.9487. Min Act: -0.1700
Data Index: 5583397 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0751. Min Range: -3.0751
Max Act: 2.9012. Min Act: -0.1700
Data Index: 3836532 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0751. Min Range: -3.0751
Max Act: 2.8853. Min Act: -0.1700
Data Index: 5830431 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0751. Min Range: -3.0751
Max Act: 2.8853. Min Act: -0.1700
Data Index: 5372313 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0751. Min Range: -3.0751
Max Act: 2.8695. Min Act: -0.1700
Data Index: 2879635 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0751. Min Range: -3.0751
Max Act: 2.8853. Min Act: -0.1700
Data Index: 4131167 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0751. Min Range: -3.0751
Max Act: 2.8695. Min Act: -0.1700
Data Index: 4822503 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0751. Min Range: -3.0751
Max Act: 2.8536. Min Act: -0.1700
Data Index: 6016947 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0751. Min Range: -3.0751
Max Act: 2.8536. Min Act: -0.1700
Data Index: 6571736 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0751. Min Range: -3.0751
Max Act: 2.8377. Min Act: -0.1700
Data Index: 3818103 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0751. Min Range: -3.0751
Max Act: 2.8536. Min Act: -0.1700
Data Index: 5947040 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0751. Min Range: -3.0751
Max Act: 2.8536. Min Act: -0.1700
Data Index: 5010575 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0751. Min Range: -3.0751
Max Act: 2.8536. Min Act: -0.1700
Data Index: 133949 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #19