Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2015 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1612. Min Range: -6.1612
Max Act: 6.1612. Min Act: -0.1700
Data Index: 6703994 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1612. Min Range: -6.1612
Max Act: 6.1300. Min Act: -0.1700
Data Index: 8756134 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1612. Min Range: -6.1612
Max Act: 6.1300. Min Act: -0.1700
Data Index: 3273413 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1612. Min Range: -6.1612
Max Act: 6.0675. Min Act: -0.1700
Data Index: 4029265 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1612. Min Range: -6.1612
Max Act: 6.0362. Min Act: -0.1700
Data Index: 698004 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1612. Min Range: -6.1612
Max Act: 6.0362. Min Act: -0.1700
Data Index: 6552361 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1612. Min Range: -6.1612
Max Act: 6.0050. Min Act: -0.1700
Data Index: 6476823 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1612. Min Range: -6.1612
Max Act: 6.0362. Min Act: -0.1700
Data Index: 2121918 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1612. Min Range: -6.1612
Max Act: 6.0050. Min Act: -0.1700
Data Index: 7243163 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1612. Min Range: -6.1612
Max Act: 5.9112. Min Act: -0.1700
Data Index: 2361763 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1612. Min Range: -6.1612
Max Act: 5.9112. Min Act: -0.1700
Data Index: 6655087 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1612. Min Range: -6.1612
Max Act: 5.8800. Min Act: -0.1700
Data Index: 2500193 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1612. Min Range: -6.1612
Max Act: 5.8487. Min Act: -0.1700
Data Index: 5625817 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1612. Min Range: -6.1612
Max Act: 5.8487. Min Act: -0.1700
Data Index: 2403413 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1612. Min Range: -6.1612
Max Act: 5.8487. Min Act: -0.1700
Data Index: 1733607 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1612. Min Range: -6.1612
Max Act: 5.8487. Min Act: -0.1700
Data Index: 6752384 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1612. Min Range: -6.1612
Max Act: 5.8175. Min Act: -0.1700
Data Index: 7179062 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1612. Min Range: -6.1612
Max Act: 5.8175. Min Act: -0.1700
Data Index: 7303736 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1612. Min Range: -6.1612
Max Act: 5.7862. Min Act: -0.1700
Data Index: 3081277 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1612. Min Range: -6.1612
Max Act: 5.7862. Min Act: -0.1700
Data Index: 6743893 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #19