Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1624 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0868. Min Range: -7.0868
Max Act: 7.0868. Min Act: -0.1700
Data Index: 1632590 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0868. Min Range: -7.0868
Max Act: 7.0555. Min Act: -0.1700
Data Index: 1519137 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0868. Min Range: -7.0868
Max Act: 7.0555. Min Act: -0.1700
Data Index: 1826123 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0868. Min Range: -7.0868
Max Act: 6.9305. Min Act: -0.1700
Data Index: 505149 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0868. Min Range: -7.0868
Max Act: 7.0243. Min Act: -0.1700
Data Index: 1730920 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0868. Min Range: -7.0868
Max Act: 6.9305. Min Act: -0.1700
Data Index: 6894931 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0868. Min Range: -7.0868
Max Act: 6.8680. Min Act: -0.1700
Data Index: 4188397 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0868. Min Range: -7.0868
Max Act: 6.8680. Min Act: -0.1700
Data Index: 628106 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0868. Min Range: -7.0868
Max Act: 6.8368. Min Act: -0.1700
Data Index: 3187639 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0868. Min Range: -7.0868
Max Act: 6.7430. Min Act: -0.1700
Data Index: 3045932 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0868. Min Range: -7.0868
Max Act: 6.7430. Min Act: -0.1700
Data Index: 292662 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0868. Min Range: -7.0868
Max Act: 6.7430. Min Act: -0.1700
Data Index: 6878671 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0868. Min Range: -7.0868
Max Act: 6.6805. Min Act: -0.1700
Data Index: 5243027 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0868. Min Range: -7.0868
Max Act: 6.7430. Min Act: -0.1700
Data Index: 8320697 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0868. Min Range: -7.0868
Max Act: 6.6805. Min Act: -0.1700
Data Index: 7072804 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0868. Min Range: -7.0868
Max Act: 6.7118. Min Act: -0.1700
Data Index: 6341040 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0868. Min Range: -7.0868
Max Act: 6.7430. Min Act: -0.1700
Data Index: 229129 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0868. Min Range: -7.0868
Max Act: 6.7118. Min Act: -0.1700
Data Index: 844273 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0868. Min Range: -7.0868
Max Act: 6.7118. Min Act: -0.1700
Data Index: 7188430 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0868. Min Range: -7.0868
Max Act: 6.6805. Min Act: -0.1700
Data Index: 1578832 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19