Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 165 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.4083. Min Range: -7.4083
Max Act: 7.4083. Min Act: -0.1700
Data Index: 6811150 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4083. Min Range: -7.4083
Max Act: 7.3458. Min Act: -0.1700
Data Index: 6585567 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4083. Min Range: -7.4083
Max Act: 7.3145. Min Act: -0.1700
Data Index: 4286544 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4083. Min Range: -7.4083
Max Act: 7.2833. Min Act: -0.1700
Data Index: 6390029 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4083. Min Range: -7.4083
Max Act: 7.2833. Min Act: -0.1700
Data Index: 7632370 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4083. Min Range: -7.4083
Max Act: 7.2208. Min Act: -0.1700
Data Index: 8382696 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4083. Min Range: -7.4083
Max Act: 7.1270. Min Act: -0.1700
Data Index: 173468 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4083. Min Range: -7.4083
Max Act: 7.0645. Min Act: -0.1700
Data Index: 3024575 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4083. Min Range: -7.4083
Max Act: 7.0020. Min Act: -0.1700
Data Index: 139592 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4083. Min Range: -7.4083
Max Act: 6.9708. Min Act: -0.1700
Data Index: 2547789 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4083. Min Range: -7.4083
Max Act: 6.9395. Min Act: -0.1700
Data Index: 4994215 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4083. Min Range: -7.4083
Max Act: 6.9083. Min Act: -0.1700
Data Index: 3443822 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4083. Min Range: -7.4083
Max Act: 6.9083. Min Act: -0.1700
Data Index: 4641863 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4083. Min Range: -7.4083
Max Act: 6.9083. Min Act: -0.1700
Data Index: 7591889 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4083. Min Range: -7.4083
Max Act: 6.8770. Min Act: -0.1700
Data Index: 8722523 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4083. Min Range: -7.4083
Max Act: 6.8770. Min Act: -0.1700
Data Index: 2053676 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4083. Min Range: -7.4083
Max Act: 6.9083. Min Act: -0.1700
Data Index: 3884947 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4083. Min Range: -7.4083
Max Act: 6.8458. Min Act: -0.1700
Data Index: 1474775 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4083. Min Range: -7.4083
Max Act: 6.8458. Min Act: -0.1700
Data Index: 673265 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4083. Min Range: -7.4083
Max Act: 6.8770. Min Act: -0.1700
Data Index: 7875880 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #19