Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1590 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1338. Min Range: -5.1338
Max Act: 5.1338. Min Act: -0.1700
Data Index: 5598648 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1338. Min Range: -5.1338
Max Act: 5.0400. Min Act: -0.1700
Data Index: 5544513 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1338. Min Range: -5.1338
Max Act: 5.0400. Min Act: -0.1700
Data Index: 6930462 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1338. Min Range: -5.1338
Max Act: 5.0400. Min Act: -0.1700
Data Index: 954598 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1338. Min Range: -5.1338
Max Act: 5.0088. Min Act: -0.1700
Data Index: 561903 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1338. Min Range: -5.1338
Max Act: 5.0088. Min Act: -0.1700
Data Index: 3627482 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1338. Min Range: -5.1338
Max Act: 5.0088. Min Act: -0.1700
Data Index: 4094226 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1338. Min Range: -5.1338
Max Act: 4.9775. Min Act: -0.1700
Data Index: 5246191 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1338. Min Range: -5.1338
Max Act: 4.9775. Min Act: -0.1700
Data Index: 4376313 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1338. Min Range: -5.1338
Max Act: 4.9775. Min Act: -0.1696
Data Index: 1565549 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1338. Min Range: -5.1338
Max Act: 4.9463. Min Act: -0.1700
Data Index: 1473 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1338. Min Range: -5.1338
Max Act: 4.9463. Min Act: -0.1700
Data Index: 4431427 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1338. Min Range: -5.1338
Max Act: 4.9150. Min Act: -0.1700
Data Index: 5747151 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1338. Min Range: -5.1338
Max Act: 4.9463. Min Act: -0.1699
Data Index: 1665278 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1338. Min Range: -5.1338
Max Act: 4.9463. Min Act: -0.1700
Data Index: 3716420 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1338. Min Range: -5.1338
Max Act: 4.9463. Min Act: -0.1700
Data Index: 4151843 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1338. Min Range: -5.1338
Max Act: 4.9150. Min Act: -0.1700
Data Index: 389544 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1338. Min Range: -5.1338
Max Act: 4.9463. Min Act: -0.1700
Data Index: 2973688 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1338. Min Range: -5.1338
Max Act: 4.9463. Min Act: -0.1700
Data Index: 2847463 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1338. Min Range: -5.1338
Max Act: 4.9463. Min Act: -0.1700
Data Index: 152664 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19