Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4186 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9017. Min Range: -4.9017
Max Act: 4.9017. Min Act: -0.1700
Data Index: 5953426 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9017. Min Range: -4.9017
Max Act: 4.8392. Min Act: -0.1700
Data Index: 3748814 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9017. Min Range: -4.9017
Max Act: 4.8705. Min Act: -0.1700
Data Index: 5312455 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9017. Min Range: -4.9017
Max Act: 4.7455. Min Act: -0.1700
Data Index: 7655777 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9017. Min Range: -4.9017
Max Act: 4.7142. Min Act: -0.1700
Data Index: 8668797 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9017. Min Range: -4.9017
Max Act: 4.7142. Min Act: -0.1700
Data Index: 1845669 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9017. Min Range: -4.9017
Max Act: 4.7142. Min Act: -0.1700
Data Index: 4212657 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9017. Min Range: -4.9017
Max Act: 4.6830. Min Act: -0.1700
Data Index: 7529389 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9017. Min Range: -4.9017
Max Act: 4.6517. Min Act: -0.1700
Data Index: 6426527 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9017. Min Range: -4.9017
Max Act: 4.6205. Min Act: -0.1700
Data Index: 1150889 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9017. Min Range: -4.9017
Max Act: 4.5892. Min Act: -0.1700
Data Index: 5938001 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9017. Min Range: -4.9017
Max Act: 4.6205. Min Act: -0.1700
Data Index: 5230074 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9017. Min Range: -4.9017
Max Act: 4.6205. Min Act: -0.1700
Data Index: 1797507 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9017. Min Range: -4.9017
Max Act: 4.6205. Min Act: -0.1700
Data Index: 8826205 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9017. Min Range: -4.9017
Max Act: 4.5580. Min Act: -0.1700
Data Index: 6775247 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9017. Min Range: -4.9017
Max Act: 4.5580. Min Act: -0.1700
Data Index: 99959 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9017. Min Range: -4.9017
Max Act: 4.5267. Min Act: -0.1700
Data Index: 3565155 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9017. Min Range: -4.9017
Max Act: 4.4955. Min Act: -0.1700
Data Index: 4446952 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9017. Min Range: -4.9017
Max Act: 4.4955. Min Act: -0.1700
Data Index: 597795 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9017. Min Range: -4.9017
Max Act: 4.4955. Min Act: -0.1700
Data Index: 7997750 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #19