Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4422 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0908. Min Range: -7.0908
Max Act: 7.0908. Min Act: -0.1700
Data Index: 2963915 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0908. Min Range: -7.0908
Max Act: 6.7158. Min Act: -0.1700
Data Index: 8168672 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0908. Min Range: -7.0908
Max Act: 6.5908. Min Act: -0.1700
Data Index: 8646317 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0908. Min Range: -7.0908
Max Act: 6.5595. Min Act: -0.1700
Data Index: 8827356 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0908. Min Range: -7.0908
Max Act: 6.4970. Min Act: -0.1700
Data Index: 121707 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0908. Min Range: -7.0908
Max Act: 6.4658. Min Act: -0.1700
Data Index: 5372613 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0908. Min Range: -7.0908
Max Act: 6.4658. Min Act: -0.1700
Data Index: 8803674 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0908. Min Range: -7.0908
Max Act: 6.3720. Min Act: -0.1700
Data Index: 4392323 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0908. Min Range: -7.0908
Max Act: 6.4033. Min Act: -0.1700
Data Index: 7061722 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0908. Min Range: -7.0908
Max Act: 6.3720. Min Act: -0.1700
Data Index: 8320357 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0908. Min Range: -7.0908
Max Act: 6.3720. Min Act: -0.1700
Data Index: 1882372 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0908. Min Range: -7.0908
Max Act: 6.3720. Min Act: -0.1700
Data Index: 1513054 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0908. Min Range: -7.0908
Max Act: 6.3408. Min Act: -0.1700
Data Index: 7350378 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0908. Min Range: -7.0908
Max Act: 6.3408. Min Act: -0.1700
Data Index: 6375254 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0908. Min Range: -7.0908
Max Act: 6.3408. Min Act: -0.1700
Data Index: 1289947 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0908. Min Range: -7.0908
Max Act: 6.3408. Min Act: -0.1700
Data Index: 2870831 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0908. Min Range: -7.0908
Max Act: 6.3408. Min Act: -0.1700
Data Index: 7350376 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0908. Min Range: -7.0908
Max Act: 6.3095. Min Act: -0.1700
Data Index: 3550618 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0908. Min Range: -7.0908
Max Act: 6.3095. Min Act: -0.1700
Data Index: 713981 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0908. Min Range: -7.0908
Max Act: 6.3095. Min Act: -0.1700
Data Index: 5868103 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #19