Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1086 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5183. Min Range: -5.5183
Max Act: 5.5183. Min Act: -0.1700
Data Index: 207821 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5183. Min Range: -5.5183
Max Act: 5.4871. Min Act: -0.1700
Data Index: 6229882 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5183. Min Range: -5.5183
Max Act: 5.2683. Min Act: -0.1700
Data Index: 1770101 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5183. Min Range: -5.5183
Max Act: 5.2683. Min Act: -0.1700
Data Index: 1770096 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5183. Min Range: -5.5183
Max Act: 5.1746. Min Act: -0.1700
Data Index: 7601581 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5183. Min Range: -5.5183
Max Act: 5.1433. Min Act: -0.1700
Data Index: 1770098 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5183. Min Range: -5.5183
Max Act: 5.0496. Min Act: -0.1700
Data Index: 1770102 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5183. Min Range: -5.5183
Max Act: 4.9558. Min Act: -0.1700
Data Index: 1770097 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5183. Min Range: -5.5183
Max Act: 4.9246. Min Act: -0.1700
Data Index: 7992353 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5183. Min Range: -5.5183
Max Act: 4.8933. Min Act: -0.1700
Data Index: 4009580 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5183. Min Range: -5.5183
Max Act: 4.8933. Min Act: -0.1700
Data Index: 7930722 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5183. Min Range: -5.5183
Max Act: 4.8621. Min Act: -0.1700
Data Index: 8706443 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5183. Min Range: -5.5183
Max Act: 4.8621. Min Act: -0.1700
Data Index: 3881031 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5183. Min Range: -5.5183
Max Act: 4.8621. Min Act: -0.1700
Data Index: 1770103 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5183. Min Range: -5.5183
Max Act: 4.7996. Min Act: -0.1700
Data Index: 8194813 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5183. Min Range: -5.5183
Max Act: 4.7996. Min Act: -0.1700
Data Index: 1436598 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5183. Min Range: -5.5183
Max Act: 4.7683. Min Act: -0.1700
Data Index: 7657981 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5183. Min Range: -5.5183
Max Act: 4.7683. Min Act: -0.1700
Data Index: 1802156 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5183. Min Range: -5.5183
Max Act: 4.7058. Min Act: -0.1700
Data Index: 3517863 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5183. Min Range: -5.5183
Max Act: 4.7683. Min Act: -0.1700
Data Index: 5642386 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19