Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2428 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.0701. Min Range: -11.0701
Max Act: 11.0701. Min Act: -0.1700
Data Index: 6517017 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.0701. Min Range: -11.0701
Max Act: 11.0701. Min Act: -0.1700
Data Index: 919887 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.0701. Min Range: -11.0701
Max Act: 11.0076. Min Act: -0.1700
Data Index: 5022138 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.0701. Min Range: -11.0701
Max Act: 10.8201. Min Act: -0.1700
Data Index: 4318705 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.0701. Min Range: -11.0701
Max Act: 10.8826. Min Act: -0.1700
Data Index: 3026222 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.0701. Min Range: -11.0701
Max Act: 10.6951. Min Act: -0.1700
Data Index: 7046340 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.0701. Min Range: -11.0701
Max Act: 10.5701. Min Act: -0.1700
Data Index: 3674265 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.0701. Min Range: -11.0701
Max Act: 10.5701. Min Act: -0.1700
Data Index: 4168021 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.0701. Min Range: -11.0701
Max Act: 10.5076. Min Act: -0.1700
Data Index: 5219902 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.0701. Min Range: -11.0701
Max Act: 10.4451. Min Act: -0.1700
Data Index: 402845 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.0701. Min Range: -11.0701
Max Act: 10.4451. Min Act: -0.1700
Data Index: 3021892 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.0701. Min Range: -11.0701
Max Act: 10.3201. Min Act: -0.1700
Data Index: 5908027 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.0701. Min Range: -11.0701
Max Act: 10.3201. Min Act: -0.1700
Data Index: 8626201 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.0701. Min Range: -11.0701
Max Act: 10.3201. Min Act: -0.1700
Data Index: 1385454 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.0701. Min Range: -11.0701
Max Act: 10.3201. Min Act: -0.1700
Data Index: 6853832 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.0701. Min Range: -11.0701
Max Act: 10.3201. Min Act: -0.1700
Data Index: 1920629 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.0701. Min Range: -11.0701
Max Act: 10.2576. Min Act: -0.1700
Data Index: 1131924 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.0701. Min Range: -11.0701
Max Act: 10.2576. Min Act: -0.1700
Data Index: 4804202 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.0701. Min Range: -11.0701
Max Act: 10.2576. Min Act: -0.1700
Data Index: 3702942 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.0701. Min Range: -11.0701
Max Act: 10.2576. Min Act: -0.1700
Data Index: 1972040 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19