Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1863 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3228. Min Range: -5.3228
Max Act: 5.3228. Min Act: -0.1700
Data Index: 7404636 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3228. Min Range: -5.3228
Max Act: 5.1665. Min Act: -0.1700
Data Index: 8791871 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3228. Min Range: -5.3228
Max Act: 5.1665. Min Act: -0.1700
Data Index: 5300925 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3228. Min Range: -5.3228
Max Act: 5.1978. Min Act: -0.1700
Data Index: 1606359 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3228. Min Range: -5.3228
Max Act: 5.1353. Min Act: -0.1700
Data Index: 5361295 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3228. Min Range: -5.3228
Max Act: 5.1665. Min Act: -0.1700
Data Index: 7633100 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3228. Min Range: -5.3228
Max Act: 5.1353. Min Act: -0.1700
Data Index: 1389427 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3228. Min Range: -5.3228
Max Act: 5.0728. Min Act: -0.1700
Data Index: 3734850 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3228. Min Range: -5.3228
Max Act: 5.0415. Min Act: -0.1700
Data Index: 4013193 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3228. Min Range: -5.3228
Max Act: 5.0415. Min Act: -0.1700
Data Index: 2862690 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3228. Min Range: -5.3228
Max Act: 4.9790. Min Act: -0.1700
Data Index: 5531483 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3228. Min Range: -5.3228
Max Act: 4.9790. Min Act: -0.1700
Data Index: 6493036 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3228. Min Range: -5.3228
Max Act: 4.9478. Min Act: -0.1700
Data Index: 3867446 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3228. Min Range: -5.3228
Max Act: 4.9478. Min Act: -0.1700
Data Index: 7983181 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3228. Min Range: -5.3228
Max Act: 4.9478. Min Act: -0.1700
Data Index: 7317551 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3228. Min Range: -5.3228
Max Act: 4.9478. Min Act: -0.1700
Data Index: 2456919 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3228. Min Range: -5.3228
Max Act: 4.9790. Min Act: -0.1700
Data Index: 5307332 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3228. Min Range: -5.3228
Max Act: 4.8853. Min Act: -0.1700
Data Index: 1514137 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3228. Min Range: -5.3228
Max Act: 4.8853. Min Act: -0.1700
Data Index: 6889074 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3228. Min Range: -5.3228
Max Act: 4.8853. Min Act: -0.1700
Data Index: 7337867 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #19