Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 802 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.4654. Min Range: -9.4654
Max Act: 9.4654. Min Act: -0.1700
Data Index: 6355670 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4654. Min Range: -9.4654
Max Act: 9.0904. Min Act: -0.1700
Data Index: 4178715 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4654. Min Range: -9.4654
Max Act: 8.8404. Min Act: -0.1700
Data Index: 1291847 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4654. Min Range: -9.4654
Max Act: 8.9029. Min Act: -0.1699
Data Index: 4108008 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4654. Min Range: -9.4654
Max Act: 8.9029. Min Act: -0.1700
Data Index: 7157447 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4654. Min Range: -9.4654
Max Act: 8.7779. Min Act: -0.1700
Data Index: 8610869 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4654. Min Range: -9.4654
Max Act: 8.7779. Min Act: -0.1700
Data Index: 4455377 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4654. Min Range: -9.4654
Max Act: 8.7154. Min Act: -0.1700
Data Index: 3908862 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4654. Min Range: -9.4654
Max Act: 8.8404. Min Act: -0.1700
Data Index: 1938956 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4654. Min Range: -9.4654
Max Act: 8.7154. Min Act: -0.1700
Data Index: 3799203 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4654. Min Range: -9.4654
Max Act: 8.7779. Min Act: -0.1699
Data Index: 4399942 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4654. Min Range: -9.4654
Max Act: 8.7154. Min Act: -0.1699
Data Index: 7650587 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4654. Min Range: -9.4654
Max Act: 8.7154. Min Act: -0.1700
Data Index: 3206244 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4654. Min Range: -9.4654
Max Act: 8.7154. Min Act: -0.1699
Data Index: 7384261 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4654. Min Range: -9.4654
Max Act: 8.5904. Min Act: -0.1699
Data Index: 7650588 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4654. Min Range: -9.4654
Max Act: 8.5904. Min Act: -0.1700
Data Index: 4709835 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4654. Min Range: -9.4654
Max Act: 8.5904. Min Act: -0.1700
Data Index: 2201069 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4654. Min Range: -9.4654
Max Act: 8.5904. Min Act: -0.1700
Data Index: 3930416 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4654. Min Range: -9.4654
Max Act: 8.6529. Min Act: -0.1698
Data Index: 2650721 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4654. Min Range: -9.4654
Max Act: 8.6529. Min Act: -0.1700
Data Index: 3743426 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #19