Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2977 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3577. Min Range: -3.3577
Max Act: 3.3577. Min Act: -0.1700
Data Index: 1832044 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3577. Min Range: -3.3577
Max Act: 3.2478. Min Act: -0.1700
Data Index: 2963102 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3577. Min Range: -3.3577
Max Act: 3.2007. Min Act: -0.1700
Data Index: 2748935 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3577. Min Range: -3.3577
Max Act: 3.2164. Min Act: -0.1700
Data Index: 855589 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3577. Min Range: -3.3577
Max Act: 3.1692. Min Act: -0.1700
Data Index: 2320447 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3577. Min Range: -3.3577
Max Act: 3.1377. Min Act: -0.1700
Data Index: 1502641 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3577. Min Range: -3.3577
Max Act: 3.2007. Min Act: -0.1700
Data Index: 2371564 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3577. Min Range: -3.3577
Max Act: 3.1062. Min Act: -0.1700
Data Index: 1208905 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3577. Min Range: -3.3577
Max Act: 3.1692. Min Act: -0.1700
Data Index: 5393478 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3577. Min Range: -3.3577
Max Act: 3.1535. Min Act: -0.1700
Data Index: 8527877 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3577. Min Range: -3.3577
Max Act: 3.1692. Min Act: -0.1700
Data Index: 250671 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3577. Min Range: -3.3577
Max Act: 3.1062. Min Act: -0.1700
Data Index: 2739779 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3577. Min Range: -3.3577
Max Act: 3.1377. Min Act: -0.1700
Data Index: 7351317 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3577. Min Range: -3.3577
Max Act: 3.0904. Min Act: -0.1700
Data Index: 1565746 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3577. Min Range: -3.3577
Max Act: 3.0904. Min Act: -0.1700
Data Index: 749237 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3577. Min Range: -3.3577
Max Act: 3.1220. Min Act: -0.1700
Data Index: 2477632 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3577. Min Range: -3.3577
Max Act: 3.1220. Min Act: -0.1700
Data Index: 6549662 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3577. Min Range: -3.3577
Max Act: 3.1062. Min Act: -0.1700
Data Index: 1922927 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3577. Min Range: -3.3577
Max Act: 3.1220. Min Act: -0.1700
Data Index: 8305194 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3577. Min Range: -3.3577
Max Act: 3.1062. Min Act: -0.1700
Data Index: 4572603 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #19