Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2488 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0919. Min Range: -5.0919
Max Act: 5.0919. Min Act: -0.1700
Data Index: 4754043 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0919. Min Range: -5.0919
Max Act: 4.9981. Min Act: -0.1700
Data Index: 7338086 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0919. Min Range: -5.0919
Max Act: 4.9669. Min Act: -0.1698
Data Index: 8586840 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0919. Min Range: -5.0919
Max Act: 4.9356. Min Act: -0.1700
Data Index: 1270699 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0919. Min Range: -5.0919
Max Act: 4.9669. Min Act: -0.1700
Data Index: 299184 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0919. Min Range: -5.0919
Max Act: 4.9669. Min Act: -0.1700
Data Index: 5421279 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0919. Min Range: -5.0919
Max Act: 4.9356. Min Act: -0.1700
Data Index: 2223318 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0919. Min Range: -5.0919
Max Act: 4.9356. Min Act: -0.1700
Data Index: 7364238 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0919. Min Range: -5.0919
Max Act: 4.9356. Min Act: -0.1698
Data Index: 1833151 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0919. Min Range: -5.0919
Max Act: 4.9356. Min Act: -0.1700
Data Index: 2548630 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0919. Min Range: -5.0919
Max Act: 4.9044. Min Act: -0.1700
Data Index: 12843 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0919. Min Range: -5.0919
Max Act: 4.9356. Min Act: -0.1700
Data Index: 628075 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0919. Min Range: -5.0919
Max Act: 4.9044. Min Act: -0.1700
Data Index: 2404307 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0919. Min Range: -5.0919
Max Act: 4.8731. Min Act: -0.1700
Data Index: 7262227 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0919. Min Range: -5.0919
Max Act: 4.8731. Min Act: -0.1700
Data Index: 2558312 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0919. Min Range: -5.0919
Max Act: 4.8731. Min Act: -0.1700
Data Index: 3152409 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0919. Min Range: -5.0919
Max Act: 4.9044. Min Act: -0.1700
Data Index: 5364610 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0919. Min Range: -5.0919
Max Act: 4.8731. Min Act: -0.1700
Data Index: 5270580 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0919. Min Range: -5.0919
Max Act: 4.8731. Min Act: -0.1700
Data Index: 2977872 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0919. Min Range: -5.0919
Max Act: 4.8731. Min Act: -0.1700
Data Index: 5101976 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19