Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3913 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2344. Min Range: -5.2344
Max Act: 5.2344. Min Act: -0.1700
Data Index: 4614561 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2344. Min Range: -5.2344
Max Act: 5.2344. Min Act: -0.1700
Data Index: 3637440 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2344. Min Range: -5.2344
Max Act: 5.1406. Min Act: -0.1700
Data Index: 4508490 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2344. Min Range: -5.2344
Max Act: 5.1094. Min Act: -0.1700
Data Index: 7562309 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2344. Min Range: -5.2344
Max Act: 5.1094. Min Act: -0.1700
Data Index: 8340562 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2344. Min Range: -5.2344
Max Act: 5.0156. Min Act: -0.1700
Data Index: 18068 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2344. Min Range: -5.2344
Max Act: 5.0469. Min Act: -0.1700
Data Index: 622010 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2344. Min Range: -5.2344
Max Act: 5.0469. Min Act: -0.1700
Data Index: 4733662 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2344. Min Range: -5.2344
Max Act: 5.0469. Min Act: -0.1700
Data Index: 634058 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2344. Min Range: -5.2344
Max Act: 5.0781. Min Act: -0.1700
Data Index: 3478890 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2344. Min Range: -5.2344
Max Act: 5.0156. Min Act: -0.1700
Data Index: 5387679 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2344. Min Range: -5.2344
Max Act: 5.0156. Min Act: -0.1700
Data Index: 4562962 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2344. Min Range: -5.2344
Max Act: 5.0156. Min Act: -0.1700
Data Index: 1879472 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2344. Min Range: -5.2344
Max Act: 5.0156. Min Act: -0.1700
Data Index: 151293 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2344. Min Range: -5.2344
Max Act: 5.0156. Min Act: -0.1700
Data Index: 6227104 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2344. Min Range: -5.2344
Max Act: 4.9844. Min Act: -0.1700
Data Index: 8416525 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2344. Min Range: -5.2344
Max Act: 4.9844. Min Act: -0.1700
Data Index: 8077139 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2344. Min Range: -5.2344
Max Act: 4.9844. Min Act: -0.1700
Data Index: 2659841 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2344. Min Range: -5.2344
Max Act: 4.9531. Min Act: -0.1700
Data Index: 6532057 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2344. Min Range: -5.2344
Max Act: 4.9531. Min Act: -0.1700
Data Index: 7050711 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #19