Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2351 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.1890. Min Range: -1.1890
Max Act: 1.1890. Min Act: -0.1700
Data Index: 312125 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1890. Min Range: -1.1890
Max Act: 1.1714. Min Act: -0.1700
Data Index: 7800410 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1890. Min Range: -1.1890
Max Act: 1.1714. Min Act: -0.1700
Data Index: 3636850 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1890. Min Range: -1.1890
Max Act: 1.1626. Min Act: -0.1700
Data Index: 7186751 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1890. Min Range: -1.1890
Max Act: 1.1626. Min Act: -0.1700
Data Index: 7651396 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1890. Min Range: -1.1890
Max Act: 1.1363. Min Act: -0.1700
Data Index: 7119582 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1890. Min Range: -1.1890
Max Act: 1.1100. Min Act: -0.1700
Data Index: 2557529 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1890. Min Range: -1.1890
Max Act: 1.1100. Min Act: -0.1700
Data Index: 3497554 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1890. Min Range: -1.1890
Max Act: 1.1012. Min Act: -0.1700
Data Index: 999672 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1890. Min Range: -1.1890
Max Act: 1.1012. Min Act: -0.1700
Data Index: 8392227 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1890. Min Range: -1.1890
Max Act: 1.1012. Min Act: -0.1700
Data Index: 8799514 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1890. Min Range: -1.1890
Max Act: 1.1012. Min Act: -0.1700
Data Index: 5997604 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1890. Min Range: -1.1890
Max Act: 1.0924. Min Act: -0.1700
Data Index: 6416258 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1890. Min Range: -1.1890
Max Act: 1.0837. Min Act: -0.1700
Data Index: 4024670 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1890. Min Range: -1.1890
Max Act: 1.0837. Min Act: -0.1700
Data Index: 1764042 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1890. Min Range: -1.1890
Max Act: 1.0662. Min Act: -0.1700
Data Index: 6821373 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1890. Min Range: -1.1890
Max Act: 1.0749. Min Act: -0.1700
Data Index: 3815808 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1890. Min Range: -1.1890
Max Act: 1.0662. Min Act: -0.1700
Data Index: 7879408 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1890. Min Range: -1.1890
Max Act: 1.0662. Min Act: -0.1700
Data Index: 7835520 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1890. Min Range: -1.1890
Max Act: 1.0662. Min Act: -0.1700
Data Index: 7886793 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #19