Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 74 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1099. Min Range: -4.1099
Max Act: 4.1099. Min Act: -0.1700
Data Index: 2448596 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1099. Min Range: -4.1099
Max Act: 4.0786. Min Act: -0.1700
Data Index: 8177469 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1099. Min Range: -4.1099
Max Act: 4.0473. Min Act: -0.1700
Data Index: 2579917 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1099. Min Range: -4.1099
Max Act: 4.0786. Min Act: -0.1700
Data Index: 6513455 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1099. Min Range: -4.1099
Max Act: 4.0473. Min Act: -0.1700
Data Index: 2668671 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1099. Min Range: -4.1099
Max Act: 3.9848. Min Act: -0.1700
Data Index: 410452 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1099. Min Range: -4.1099
Max Act: 3.9848. Min Act: -0.1700
Data Index: 5332570 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1099. Min Range: -4.1099
Max Act: 3.9848. Min Act: -0.1700
Data Index: 1435312 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1099. Min Range: -4.1099
Max Act: 3.9536. Min Act: -0.1700
Data Index: 7190002 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1099. Min Range: -4.1099
Max Act: 3.9536. Min Act: -0.1700
Data Index: 1320084 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1099. Min Range: -4.1099
Max Act: 3.9223. Min Act: -0.1700
Data Index: 8583380 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1099. Min Range: -4.1099
Max Act: 3.8910. Min Act: -0.1700
Data Index: 5205844 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1099. Min Range: -4.1099
Max Act: 3.9223. Min Act: -0.1700
Data Index: 1262905 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1099. Min Range: -4.1099
Max Act: 3.9223. Min Act: -0.1700
Data Index: 6203880 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1099. Min Range: -4.1099
Max Act: 3.9223. Min Act: -0.1700
Data Index: 4000391 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1099. Min Range: -4.1099
Max Act: 3.8910. Min Act: -0.1700
Data Index: 1007765 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1099. Min Range: -4.1099
Max Act: 3.8910. Min Act: -0.1700
Data Index: 5891874 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1099. Min Range: -4.1099
Max Act: 3.8910. Min Act: -0.1700
Data Index: 84613 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1099. Min Range: -4.1099
Max Act: 3.8598. Min Act: -0.1700
Data Index: 5996112 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1099. Min Range: -4.1099
Max Act: 3.8910. Min Act: -0.1700
Data Index: 6089918 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #19