Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3250 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9643. Min Range: -3.9643
Max Act: 3.9330. Min Act: -0.1700
Data Index: 5805894 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9643. Min Range: -3.9643
Max Act: 3.9017. Min Act: -0.1700
Data Index: 7876558 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9643. Min Range: -3.9643
Max Act: 3.9643. Min Act: -0.1700
Data Index: 2524810 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9643. Min Range: -3.9643
Max Act: 3.9330. Min Act: -0.1700
Data Index: 2874475 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9643. Min Range: -3.9643
Max Act: 3.9017. Min Act: -0.1700
Data Index: 636914 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9643. Min Range: -3.9643
Max Act: 3.9017. Min Act: -0.1700
Data Index: 2544391 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9643. Min Range: -3.9643
Max Act: 3.9017. Min Act: -0.1700
Data Index: 5018745 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9643. Min Range: -3.9643
Max Act: 3.9017. Min Act: -0.1700
Data Index: 237453 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9643. Min Range: -3.9643
Max Act: 3.9017. Min Act: -0.1700
Data Index: 7174909 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9643. Min Range: -3.9643
Max Act: 3.9017. Min Act: -0.1700
Data Index: 631425 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9643. Min Range: -3.9643
Max Act: 3.9017. Min Act: -0.1700
Data Index: 3533223 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9643. Min Range: -3.9643
Max Act: 3.8705. Min Act: -0.1700
Data Index: 3402546 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9643. Min Range: -3.9643
Max Act: 3.8705. Min Act: -0.1700
Data Index: 1611127 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9643. Min Range: -3.9643
Max Act: 3.9017. Min Act: -0.1700
Data Index: 3348932 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9643. Min Range: -3.9643
Max Act: 3.9017. Min Act: -0.1700
Data Index: 821744 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9643. Min Range: -3.9643
Max Act: 3.9017. Min Act: -0.1700
Data Index: 6191769 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9643. Min Range: -3.9643
Max Act: 3.9017. Min Act: -0.1700
Data Index: 6086926 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9643. Min Range: -3.9643
Max Act: 3.9017. Min Act: -0.1700
Data Index: 2821360 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9643. Min Range: -3.9643
Max Act: 3.9017. Min Act: -0.1700
Data Index: 506153 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9643. Min Range: -3.9643
Max Act: 3.9017. Min Act: -0.1700
Data Index: 956026 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19