Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1715 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3115. Min Range: -3.3115
Max Act: 3.3115. Min Act: -0.1700
Data Index: 3420344 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3115. Min Range: -3.3115
Max Act: 3.1701. Min Act: -0.1700
Data Index: 6403351 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3115. Min Range: -3.3115
Max Act: 3.1386. Min Act: -0.1700
Data Index: 6736425 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3115. Min Range: -3.3115
Max Act: 3.1071. Min Act: -0.1700
Data Index: 6333561 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3115. Min Range: -3.3115
Max Act: 3.0756. Min Act: -0.1700
Data Index: 7413014 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3115. Min Range: -3.3115
Max Act: 3.0756. Min Act: -0.1700
Data Index: 8073833 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3115. Min Range: -3.3115
Max Act: 3.0440. Min Act: -0.1700
Data Index: 5827911 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3115. Min Range: -3.3115
Max Act: 3.0440. Min Act: -0.1700
Data Index: 1009546 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3115. Min Range: -3.3115
Max Act: 3.0282. Min Act: -0.1700
Data Index: 1350425 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3115. Min Range: -3.3115
Max Act: 3.0124. Min Act: -0.1700
Data Index: 5942892 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3115. Min Range: -3.3115
Max Act: 2.9966. Min Act: -0.1700
Data Index: 6165571 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3115. Min Range: -3.3115
Max Act: 2.9808. Min Act: -0.1700
Data Index: 2955537 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3115. Min Range: -3.3115
Max Act: 2.9333. Min Act: -0.1700
Data Index: 2807982 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3115. Min Range: -3.3115
Max Act: 2.9492. Min Act: -0.1700
Data Index: 7767186 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3115. Min Range: -3.3115
Max Act: 2.9650. Min Act: -0.1700
Data Index: 4221455 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3115. Min Range: -3.3115
Max Act: 2.9808. Min Act: -0.1700
Data Index: 5256211 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3115. Min Range: -3.3115
Max Act: 2.9966. Min Act: -0.1700
Data Index: 1372872 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3115. Min Range: -3.3115
Max Act: 2.9333. Min Act: -0.1700
Data Index: 3827598 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3115. Min Range: -3.3115
Max Act: 2.9492. Min Act: -0.1700
Data Index: 1872943 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3115. Min Range: -3.3115
Max Act: 2.9492. Min Act: -0.1700
Data Index: 6769667 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #19