Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1120 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1709. Min Range: -3.1709
Max Act: 3.1709. Min Act: -0.1700
Data Index: 7912587 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1709. Min Range: -3.1709
Max Act: 3.1709. Min Act: -0.1700
Data Index: 1109697 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1709. Min Range: -3.1709
Max Act: 3.0449. Min Act: -0.1700
Data Index: 7912586 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1709. Min Range: -3.1709
Max Act: 3.0291. Min Act: -0.1700
Data Index: 75314 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1709. Min Range: -3.1709
Max Act: 3.0133. Min Act: -0.1700
Data Index: 4757349 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1709. Min Range: -3.1709
Max Act: 2.9817. Min Act: -0.1700
Data Index: 837780 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1709. Min Range: -3.1709
Max Act: 2.9659. Min Act: -0.1700
Data Index: 4718136 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1709. Min Range: -3.1709
Max Act: 2.9659. Min Act: -0.1700
Data Index: 3174832 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1709. Min Range: -3.1709
Max Act: 2.9342. Min Act: -0.1700
Data Index: 8185354 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1709. Min Range: -3.1709
Max Act: 2.8866. Min Act: -0.1700
Data Index: 2562531 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1709. Min Range: -3.1709
Max Act: 2.9025. Min Act: -0.1700
Data Index: 1074962 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1709. Min Range: -3.1709
Max Act: 2.9025. Min Act: -0.1700
Data Index: 1749488 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1709. Min Range: -3.1709
Max Act: 2.9184. Min Act: -0.1700
Data Index: 4319664 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1709. Min Range: -3.1709
Max Act: 2.8866. Min Act: -0.1700
Data Index: 8296578 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1709. Min Range: -3.1709
Max Act: 2.8866. Min Act: -0.1700
Data Index: 7740224 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1709. Min Range: -3.1709
Max Act: 2.8549. Min Act: -0.1700
Data Index: 7048372 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1709. Min Range: -3.1709
Max Act: 2.8390. Min Act: -0.1700
Data Index: 4753714 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1709. Min Range: -3.1709
Max Act: 2.8549. Min Act: -0.1700
Data Index: 4850767 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1709. Min Range: -3.1709
Max Act: 2.8708. Min Act: -0.1700
Data Index: 225962 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1709. Min Range: -3.1709
Max Act: 2.8708. Min Act: -0.1700
Data Index: 1249473 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19