Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1071 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8746. Min Range: -3.8746
Max Act: 3.8746. Min Act: -0.1700
Data Index: 5207629 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8746. Min Range: -3.8746
Max Act: 3.8746. Min Act: -0.1700
Data Index: 3883892 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8746. Min Range: -3.8746
Max Act: 3.8746. Min Act: -0.1700
Data Index: 1154250 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8746. Min Range: -3.8746
Max Act: 3.7652. Min Act: -0.1700
Data Index: 925556 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8746. Min Range: -3.8746
Max Act: 3.7652. Min Act: -0.1700
Data Index: 7937331 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8746. Min Range: -3.8746
Max Act: 3.7495. Min Act: -0.1700
Data Index: 2622611 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8746. Min Range: -3.8746
Max Act: 3.7495. Min Act: -0.1700
Data Index: 7844831 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8746. Min Range: -3.8746
Max Act: 3.7339. Min Act: -0.1700
Data Index: 4170849 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8746. Min Range: -3.8746
Max Act: 3.7183. Min Act: -0.1700
Data Index: 2291460 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8746. Min Range: -3.8746
Max Act: 3.7339. Min Act: -0.1700
Data Index: 2596501 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8746. Min Range: -3.8746
Max Act: 3.7339. Min Act: -0.1700
Data Index: 4740426 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8746. Min Range: -3.8746
Max Act: 3.7495. Min Act: -0.1700
Data Index: 1403827 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8746. Min Range: -3.8746
Max Act: 3.7183. Min Act: -0.1700
Data Index: 6842462 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8746. Min Range: -3.8746
Max Act: 3.7183. Min Act: -0.1700
Data Index: 5527047 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8746. Min Range: -3.8746
Max Act: 3.7026. Min Act: -0.1700
Data Index: 4170842 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8746. Min Range: -3.8746
Max Act: 3.6870. Min Act: -0.1700
Data Index: 4223906 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8746. Min Range: -3.8746
Max Act: 3.6870. Min Act: -0.1700
Data Index: 8763903 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8746. Min Range: -3.8746
Max Act: 3.7026. Min Act: -0.1700
Data Index: 1458052 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8746. Min Range: -3.8746
Max Act: 3.6870. Min Act: -0.1700
Data Index: 3642035 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8746. Min Range: -3.8746
Max Act: 3.6870. Min Act: -0.1700
Data Index: 7586748 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19