Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1846 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7794. Min Range: -5.7794
Max Act: 5.7794. Min Act: -0.1700
Data Index: 474415 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7794. Min Range: -5.7794
Max Act: 5.6231. Min Act: -0.1700
Data Index: 2345000 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7794. Min Range: -5.7794
Max Act: 5.6231. Min Act: -0.1700
Data Index: 5339259 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7794. Min Range: -5.7794
Max Act: 5.6231. Min Act: -0.1700
Data Index: 6506794 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7794. Min Range: -5.7794
Max Act: 5.5606. Min Act: -0.1700
Data Index: 4590639 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7794. Min Range: -5.7794
Max Act: 5.5606. Min Act: -0.1700
Data Index: 6906385 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7794. Min Range: -5.7794
Max Act: 5.5294. Min Act: -0.1700
Data Index: 3785372 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7794. Min Range: -5.7794
Max Act: 5.5606. Min Act: -0.1700
Data Index: 7561502 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7794. Min Range: -5.7794
Max Act: 5.4981. Min Act: -0.1700
Data Index: 2013047 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7794. Min Range: -5.7794
Max Act: 5.5294. Min Act: -0.1700
Data Index: 3233851 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7794. Min Range: -5.7794
Max Act: 5.4981. Min Act: -0.1700
Data Index: 602832 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7794. Min Range: -5.7794
Max Act: 5.4981. Min Act: -0.1700
Data Index: 7942323 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7794. Min Range: -5.7794
Max Act: 5.5294. Min Act: -0.1700
Data Index: 6107852 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7794. Min Range: -5.7794
Max Act: 5.4981. Min Act: -0.1700
Data Index: 7885128 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7794. Min Range: -5.7794
Max Act: 5.4981. Min Act: -0.1700
Data Index: 5437419 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7794. Min Range: -5.7794
Max Act: 5.4669. Min Act: -0.1700
Data Index: 6094088 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7794. Min Range: -5.7794
Max Act: 5.4356. Min Act: -0.1700
Data Index: 5845198 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7794. Min Range: -5.7794
Max Act: 5.4669. Min Act: -0.1700
Data Index: 5147262 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7794. Min Range: -5.7794
Max Act: 5.4356. Min Act: -0.1700
Data Index: 952404 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7794. Min Range: -5.7794
Max Act: 5.4981. Min Act: -0.1700
Data Index: 3855138 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #19