Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4214 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8773. Min Range: -4.8773
Max Act: 4.8773. Min Act: -0.1700
Data Index: 756842 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8773. Min Range: -4.8773
Max Act: 4.8460. Min Act: -0.1700
Data Index: 4371278 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8773. Min Range: -4.8773
Max Act: 4.8148. Min Act: -0.1700
Data Index: 3313189 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8773. Min Range: -4.8773
Max Act: 4.7835. Min Act: -0.1700
Data Index: 3076256 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8773. Min Range: -4.8773
Max Act: 4.7523. Min Act: -0.1700
Data Index: 6958149 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8773. Min Range: -4.8773
Max Act: 4.6898. Min Act: -0.1700
Data Index: 7116345 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8773. Min Range: -4.8773
Max Act: 4.6898. Min Act: -0.1700
Data Index: 1914104 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8773. Min Range: -4.8773
Max Act: 4.6898. Min Act: -0.1700
Data Index: 5470845 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8773. Min Range: -4.8773
Max Act: 4.7210. Min Act: -0.1700
Data Index: 6897105 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8773. Min Range: -4.8773
Max Act: 4.6585. Min Act: -0.1700
Data Index: 6249936 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8773. Min Range: -4.8773
Max Act: 4.6273. Min Act: -0.1700
Data Index: 8005045 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8773. Min Range: -4.8773
Max Act: 4.6898. Min Act: -0.1700
Data Index: 5777085 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8773. Min Range: -4.8773
Max Act: 4.6273. Min Act: -0.1700
Data Index: 6572179 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8773. Min Range: -4.8773
Max Act: 4.5960. Min Act: -0.1700
Data Index: 5918741 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8773. Min Range: -4.8773
Max Act: 4.5960. Min Act: -0.1700
Data Index: 4075384 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8773. Min Range: -4.8773
Max Act: 4.5960. Min Act: -0.1700
Data Index: 8376579 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8773. Min Range: -4.8773
Max Act: 4.5960. Min Act: -0.1700
Data Index: 543366 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8773. Min Range: -4.8773
Max Act: 4.5648. Min Act: -0.1700
Data Index: 8006136 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8773. Min Range: -4.8773
Max Act: 4.5648. Min Act: -0.1700
Data Index: 1205055 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8773. Min Range: -4.8773
Max Act: 4.5335. Min Act: -0.1700
Data Index: 5089387 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19