Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2851 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3838. Min Range: -4.3838
Max Act: 4.3838. Min Act: -0.1700
Data Index: 5131867 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3838. Min Range: -4.3838
Max Act: 4.2901. Min Act: -0.1700
Data Index: 6958817 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3838. Min Range: -4.3838
Max Act: 4.2901. Min Act: -0.1700
Data Index: 1941517 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3838. Min Range: -4.3838
Max Act: 4.1963. Min Act: -0.1700
Data Index: 2767477 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3838. Min Range: -4.3838
Max Act: 4.1963. Min Act: -0.1700
Data Index: 3381232 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3838. Min Range: -4.3838
Max Act: 4.1651. Min Act: -0.1700
Data Index: 79950 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3838. Min Range: -4.3838
Max Act: 4.1026. Min Act: -0.1700
Data Index: 1602054 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3838. Min Range: -4.3838
Max Act: 4.0713. Min Act: -0.1700
Data Index: 7384906 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3838. Min Range: -4.3838
Max Act: 4.0088. Min Act: -0.1700
Data Index: 3179654 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3838. Min Range: -4.3838
Max Act: 4.0400. Min Act: -0.1700
Data Index: 4239800 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3838. Min Range: -4.3838
Max Act: 3.9150. Min Act: -0.1700
Data Index: 3341432 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3838. Min Range: -4.3838
Max Act: 3.9150. Min Act: -0.1700
Data Index: 2418467 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3838. Min Range: -4.3838
Max Act: 3.9150. Min Act: -0.1700
Data Index: 4953253 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3838. Min Range: -4.3838
Max Act: 3.9150. Min Act: -0.1700
Data Index: 8527227 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3838. Min Range: -4.3838
Max Act: 3.8837. Min Act: -0.1700
Data Index: 136912 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3838. Min Range: -4.3838
Max Act: 3.8837. Min Act: -0.1700
Data Index: 3661201 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3838. Min Range: -4.3838
Max Act: 3.8525. Min Act: -0.1700
Data Index: 4122699 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3838. Min Range: -4.3838
Max Act: 3.8837. Min Act: -0.1700
Data Index: 5222373 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3838. Min Range: -4.3838
Max Act: 3.8837. Min Act: -0.1700
Data Index: 2471142 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3838. Min Range: -4.3838
Max Act: 3.8525. Min Act: -0.1700
Data Index: 1683107 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19