Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6217 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9699. Min Range: -8.9699
Max Act: 8.9699. Min Act: -0.1700
Data Index: 1870658 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9699. Min Range: -8.9699
Max Act: 8.9074. Min Act: -0.1700
Data Index: 5412357 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9699. Min Range: -8.9699
Max Act: 8.8449. Min Act: -0.1700
Data Index: 3027598 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9699. Min Range: -8.9699
Max Act: 8.8449. Min Act: -0.1700
Data Index: 7406768 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9699. Min Range: -8.9699
Max Act: 8.8449. Min Act: -0.1700
Data Index: 3757090 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9699. Min Range: -8.9699
Max Act: 8.7199. Min Act: -0.1700
Data Index: 3789324 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9699. Min Range: -8.9699
Max Act: 8.7199. Min Act: -0.1700
Data Index: 4185310 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9699. Min Range: -8.9699
Max Act: 8.6574. Min Act: -0.1700
Data Index: 7867374 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9699. Min Range: -8.9699
Max Act: 8.6574. Min Act: -0.1700
Data Index: 5364089 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9699. Min Range: -8.9699
Max Act: 8.5949. Min Act: -0.1700
Data Index: 1035709 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9699. Min Range: -8.9699
Max Act: 8.5949. Min Act: -0.1700
Data Index: 1703796 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9699. Min Range: -8.9699
Max Act: 8.5949. Min Act: -0.1700
Data Index: 2769427 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9699. Min Range: -8.9699
Max Act: 8.5324. Min Act: -0.1700
Data Index: 1950923 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9699. Min Range: -8.9699
Max Act: 8.4699. Min Act: -0.1700
Data Index: 4601703 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9699. Min Range: -8.9699
Max Act: 8.5324. Min Act: -0.1700
Data Index: 5937858 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9699. Min Range: -8.9699
Max Act: 8.4699. Min Act: -0.1700
Data Index: 4592046 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9699. Min Range: -8.9699
Max Act: 8.4699. Min Act: -0.1700
Data Index: 5456200 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9699. Min Range: -8.9699
Max Act: 8.4699. Min Act: -0.1700
Data Index: 5385163 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9699. Min Range: -8.9699
Max Act: 8.4699. Min Act: -0.1700
Data Index: 7620744 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9699. Min Range: -8.9699
Max Act: 8.4699. Min Act: -0.1700
Data Index: 7010546 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #19