Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5765. Min Range: -5.5765
Max Act: 5.5765. Min Act: -0.1700
Data Index: 7681330 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5765. Min Range: -5.5765
Max Act: 5.5140. Min Act: -0.1700
Data Index: 7921977 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5765. Min Range: -5.5765
Max Act: 5.4515. Min Act: -0.1700
Data Index: 3864266 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5765. Min Range: -5.5765
Max Act: 5.4515. Min Act: -0.1700
Data Index: 2883137 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5765. Min Range: -5.5765
Max Act: 5.4828. Min Act: -0.1700
Data Index: 2810742 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5765. Min Range: -5.5765
Max Act: 5.4515. Min Act: -0.1700
Data Index: 2932138 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5765. Min Range: -5.5765
Max Act: 5.3890. Min Act: -0.1700
Data Index: 2054908 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5765. Min Range: -5.5765
Max Act: 5.3578. Min Act: -0.1700
Data Index: 7814606 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5765. Min Range: -5.5765
Max Act: 5.3578. Min Act: -0.1700
Data Index: 5863337 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5765. Min Range: -5.5765
Max Act: 5.3265. Min Act: -0.1700
Data Index: 6617070 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5765. Min Range: -5.5765
Max Act: 5.2953. Min Act: -0.1700
Data Index: 3177577 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5765. Min Range: -5.5765
Max Act: 5.2953. Min Act: -0.1700
Data Index: 5558565 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5765. Min Range: -5.5765
Max Act: 5.2953. Min Act: -0.1700
Data Index: 4802276 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5765. Min Range: -5.5765
Max Act: 5.2640. Min Act: -0.1700
Data Index: 1172235 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5765. Min Range: -5.5765
Max Act: 5.2640. Min Act: -0.1700
Data Index: 257519 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5765. Min Range: -5.5765
Max Act: 5.2328. Min Act: -0.1700
Data Index: 5222173 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5765. Min Range: -5.5765
Max Act: 5.2328. Min Act: -0.1700
Data Index: 8782944 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5765. Min Range: -5.5765
Max Act: 5.2328. Min Act: -0.1700
Data Index: 3992361 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5765. Min Range: -5.5765
Max Act: 5.2015. Min Act: -0.1700
Data Index: 7275587 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5765. Min Range: -5.5765
Max Act: 5.2015. Min Act: -0.1700
Data Index: 2716686 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #19