Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3254 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.8358. Min Range: -1.8358
Max Act: 1.8358. Min Act: -0.1700
Data Index: 389890 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8358. Min Range: -1.8358
Max Act: 1.7756. Min Act: -0.1700
Data Index: 8628464 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8358. Min Range: -1.8358
Max Act: 1.7756. Min Act: -0.1700
Data Index: 2781450 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8358. Min Range: -1.8358
Max Act: 1.7756. Min Act: -0.1700
Data Index: 2404625 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8358. Min Range: -1.8358
Max Act: 1.7583. Min Act: -0.1700
Data Index: 2781445 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8358. Min Range: -1.8358
Max Act: 1.7670. Min Act: -0.1700
Data Index: 638720 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8358. Min Range: -1.8358
Max Act: 1.7583. Min Act: -0.1700
Data Index: 3847391 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8358. Min Range: -1.8358
Max Act: 1.7497. Min Act: -0.1700
Data Index: 1204248 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8358. Min Range: -1.8358
Max Act: 1.7583. Min Act: -0.1700
Data Index: 2715962 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8358. Min Range: -1.8358
Max Act: 1.7497. Min Act: -0.1700
Data Index: 4406812 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8358. Min Range: -1.8358
Max Act: 1.7411. Min Act: -0.1700
Data Index: 3217513 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8358. Min Range: -1.8358
Max Act: 1.7411. Min Act: -0.1696
Data Index: 4437323 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8358. Min Range: -1.8358
Max Act: 1.7497. Min Act: -0.1700
Data Index: 2838983 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8358. Min Range: -1.8358
Max Act: 1.7411. Min Act: -0.1700
Data Index: 6546435 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8358. Min Range: -1.8358
Max Act: 1.7411. Min Act: -0.1700
Data Index: 7799510 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8358. Min Range: -1.8358
Max Act: 1.7324. Min Act: -0.1700
Data Index: 3105488 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8358. Min Range: -1.8358
Max Act: 1.7324. Min Act: -0.1700
Data Index: 3284244 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8358. Min Range: -1.8358
Max Act: 1.7324. Min Act: -0.1700
Data Index: 7085846 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8358. Min Range: -1.8358
Max Act: 1.7324. Min Act: -0.1700
Data Index: 7085841 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8358. Min Range: -1.8358
Max Act: 1.7151. Min Act: -0.1700
Data Index: 94825 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #19