Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 804 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1206. Min Range: -4.1206
Max Act: 4.0893. Min Act: -0.1700
Data Index: 2105829 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1206. Min Range: -4.1206
Max Act: 4.1206. Min Act: -0.1700
Data Index: 8619450 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1206. Min Range: -4.1206
Max Act: 4.1206. Min Act: -0.1700
Data Index: 1716371 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1206. Min Range: -4.1206
Max Act: 4.1206. Min Act: -0.1700
Data Index: 4129339 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1206. Min Range: -4.1206
Max Act: 4.1206. Min Act: -0.1700
Data Index: 2164154 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1206. Min Range: -4.1206
Max Act: 4.0893. Min Act: -0.1700
Data Index: 7965594 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1206. Min Range: -4.1206
Max Act: 4.0581. Min Act: -0.1700
Data Index: 4539201 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1206. Min Range: -4.1206
Max Act: 4.0893. Min Act: -0.1700
Data Index: 8612620 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1206. Min Range: -4.1206
Max Act: 4.0893. Min Act: -0.1700
Data Index: 3785568 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1206. Min Range: -4.1206
Max Act: 4.0893. Min Act: -0.1700
Data Index: 1692923 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1206. Min Range: -4.1206
Max Act: 3.9956. Min Act: -0.1700
Data Index: 4060420 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1206. Min Range: -4.1206
Max Act: 4.0893. Min Act: -0.1700
Data Index: 813660 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1206. Min Range: -4.1206
Max Act: 4.0581. Min Act: -0.1700
Data Index: 4686046 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1206. Min Range: -4.1206
Max Act: 4.0581. Min Act: -0.1700
Data Index: 2756846 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1206. Min Range: -4.1206
Max Act: 4.0581. Min Act: -0.1700
Data Index: 5002933 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1206. Min Range: -4.1206
Max Act: 4.0581. Min Act: -0.1700
Data Index: 3060609 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1206. Min Range: -4.1206
Max Act: 4.0581. Min Act: -0.1700
Data Index: 5484935 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1206. Min Range: -4.1206
Max Act: 4.0268. Min Act: -0.1700
Data Index: 2658197 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1206. Min Range: -4.1206
Max Act: 4.0268. Min Act: -0.1700
Data Index: 74351 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1206. Min Range: -4.1206
Max Act: 3.9956. Min Act: -0.1700
Data Index: 11668 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19