Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1591 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9894. Min Range: -5.9894
Max Act: 5.9894. Min Act: -0.1700
Data Index: 1047629 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9894. Min Range: -5.9894
Max Act: 5.8019. Min Act: -0.1700
Data Index: 774906 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9894. Min Range: -5.9894
Max Act: 5.4269. Min Act: -0.1700
Data Index: 4248239 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9894. Min Range: -5.9894
Max Act: 5.4269. Min Act: -0.1700
Data Index: 668642 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9894. Min Range: -5.9894
Max Act: 5.3644. Min Act: -0.1700
Data Index: 5154193 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9894. Min Range: -5.9894
Max Act: 5.3956. Min Act: -0.1700
Data Index: 5693139 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9894. Min Range: -5.9894
Max Act: 5.3644. Min Act: -0.1700
Data Index: 3860925 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9894. Min Range: -5.9894
Max Act: 5.3644. Min Act: -0.1700
Data Index: 5991674 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9894. Min Range: -5.9894
Max Act: 5.3331. Min Act: -0.1700
Data Index: 2439337 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9894. Min Range: -5.9894
Max Act: 5.3331. Min Act: -0.1700
Data Index: 1450893 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9894. Min Range: -5.9894
Max Act: 5.3019. Min Act: -0.1700
Data Index: 3115710 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9894. Min Range: -5.9894
Max Act: 5.2706. Min Act: -0.1700
Data Index: 8346212 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9894. Min Range: -5.9894
Max Act: 5.2394. Min Act: -0.1700
Data Index: 7939393 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9894. Min Range: -5.9894
Max Act: 5.2706. Min Act: -0.1700
Data Index: 7603615 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9894. Min Range: -5.9894
Max Act: 5.2706. Min Act: -0.1700
Data Index: 7326048 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9894. Min Range: -5.9894
Max Act: 5.2394. Min Act: -0.1700
Data Index: 2469800 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9894. Min Range: -5.9894
Max Act: 5.2081. Min Act: -0.1700
Data Index: 4111800 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9894. Min Range: -5.9894
Max Act: 5.2081. Min Act: -0.1700
Data Index: 4168977 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9894. Min Range: -5.9894
Max Act: 5.2394. Min Act: -0.1700
Data Index: 1665956 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9894. Min Range: -5.9894
Max Act: 5.2394. Min Act: -0.1700
Data Index: 7184552 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19