Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3371 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8833. Min Range: -2.8833
Max Act: 2.8833. Min Act: -0.1700
Data Index: 1879314 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8833. Min Range: -2.8833
Max Act: 2.8833. Min Act: -0.1700
Data Index: 1697247 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8833. Min Range: -2.8833
Max Act: 2.8516. Min Act: -0.1700
Data Index: 7973024 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8833. Min Range: -2.8833
Max Act: 2.8516. Min Act: -0.1700
Data Index: 4052062 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8833. Min Range: -2.8833
Max Act: 2.8039. Min Act: -0.1700
Data Index: 8242596 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8833. Min Range: -2.8833
Max Act: 2.8198. Min Act: -0.1700
Data Index: 2233991 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8833. Min Range: -2.8833
Max Act: 2.8198. Min Act: -0.1700
Data Index: 2068212 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8833. Min Range: -2.8833
Max Act: 2.8039. Min Act: -0.1700
Data Index: 1166955 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8833. Min Range: -2.8833
Max Act: 2.7879. Min Act: -0.1700
Data Index: 100845 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8833. Min Range: -2.8833
Max Act: 2.8039. Min Act: -0.1700
Data Index: 6367718 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8833. Min Range: -2.8833
Max Act: 2.7879. Min Act: -0.1700
Data Index: 5489837 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8833. Min Range: -2.8833
Max Act: 2.7720. Min Act: -0.1700
Data Index: 5721435 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8833. Min Range: -2.8833
Max Act: 2.7879. Min Act: -0.1700
Data Index: 5721437 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8833. Min Range: -2.8833
Max Act: 2.7879. Min Act: -0.1700
Data Index: 6733524 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8833. Min Range: -2.8833
Max Act: 2.7720. Min Act: -0.1700
Data Index: 1451633 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8833. Min Range: -2.8833
Max Act: 2.7720. Min Act: -0.1700
Data Index: 1879316 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8833. Min Range: -2.8833
Max Act: 2.7561. Min Act: -0.1700
Data Index: 3114468 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8833. Min Range: -2.8833
Max Act: 2.7720. Min Act: -0.1700
Data Index: 826771 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8833. Min Range: -2.8833
Max Act: 2.7720. Min Act: -0.1700
Data Index: 5489839 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8833. Min Range: -2.8833
Max Act: 2.7879. Min Act: -0.1700
Data Index: 1836442 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #19