Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1405 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2121. Min Range: -4.2121
Max Act: 4.1184. Min Act: -0.1700
Data Index: 4392124 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2121. Min Range: -4.2121
Max Act: 4.2121. Min Act: -0.1700
Data Index: 3415284 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2121. Min Range: -4.2121
Max Act: 4.1496. Min Act: -0.1700
Data Index: 275962 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2121. Min Range: -4.2121
Max Act: 4.0871. Min Act: -0.1700
Data Index: 4102846 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2121. Min Range: -4.2121
Max Act: 4.0871. Min Act: -0.1700
Data Index: 2759613 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2121. Min Range: -4.2121
Max Act: 4.1184. Min Act: -0.1700
Data Index: 3832845 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2121. Min Range: -4.2121
Max Act: 4.1496. Min Act: -0.1700
Data Index: 6515671 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2121. Min Range: -4.2121
Max Act: 4.1184. Min Act: -0.1700
Data Index: 4874274 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2121. Min Range: -4.2121
Max Act: 4.1184. Min Act: -0.1700
Data Index: 5882045 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2121. Min Range: -4.2121
Max Act: 4.1496. Min Act: -0.1700
Data Index: 3942238 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2121. Min Range: -4.2121
Max Act: 4.1809. Min Act: -0.1700
Data Index: 5765785 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2121. Min Range: -4.2121
Max Act: 4.1184. Min Act: -0.1700
Data Index: 3553477 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2121. Min Range: -4.2121
Max Act: 4.0871. Min Act: -0.1700
Data Index: 4092680 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2121. Min Range: -4.2121
Max Act: 4.0871. Min Act: -0.1700
Data Index: 4358898 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2121. Min Range: -4.2121
Max Act: 4.0559. Min Act: -0.1700
Data Index: 4231894 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2121. Min Range: -4.2121
Max Act: 4.1184. Min Act: -0.1700
Data Index: 7220500 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2121. Min Range: -4.2121
Max Act: 4.0871. Min Act: -0.1700
Data Index: 823661 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2121. Min Range: -4.2121
Max Act: 4.0871. Min Act: -0.1700
Data Index: 4127197 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2121. Min Range: -4.2121
Max Act: 4.1184. Min Act: -0.1700
Data Index: 1324524 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2121. Min Range: -4.2121
Max Act: 4.0559. Min Act: -0.1700
Data Index: 7230367 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #19