Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3570 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2705. Min Range: -4.2705
Max Act: 4.2705. Min Act: -0.1700
Data Index: 3312663 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2705. Min Range: -4.2705
Max Act: 4.2392. Min Act: -0.1700
Data Index: 74454 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2705. Min Range: -4.2705
Max Act: 4.2080. Min Act: -0.1700
Data Index: 7666525 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2705. Min Range: -4.2705
Max Act: 4.1455. Min Act: -0.1700
Data Index: 7613408 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2705. Min Range: -4.2705
Max Act: 4.1455. Min Act: -0.1700
Data Index: 5310150 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2705. Min Range: -4.2705
Max Act: 4.1142. Min Act: -0.1700
Data Index: 8256715 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2705. Min Range: -4.2705
Max Act: 4.0830. Min Act: -0.1700
Data Index: 2931580 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2705. Min Range: -4.2705
Max Act: 4.0517. Min Act: -0.1700
Data Index: 6411412 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2705. Min Range: -4.2705
Max Act: 4.0517. Min Act: -0.1700
Data Index: 7886105 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2705. Min Range: -4.2705
Max Act: 4.0204. Min Act: -0.1700
Data Index: 1629471 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2705. Min Range: -4.2705
Max Act: 3.9892. Min Act: -0.1700
Data Index: 8055273 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2705. Min Range: -4.2705
Max Act: 3.9892. Min Act: -0.1700
Data Index: 2020011 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2705. Min Range: -4.2705
Max Act: 3.9892. Min Act: -0.1700
Data Index: 5821667 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2705. Min Range: -4.2705
Max Act: 4.0204. Min Act: -0.1700
Data Index: 2470920 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2705. Min Range: -4.2705
Max Act: 3.9579. Min Act: -0.1700
Data Index: 6472210 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2705. Min Range: -4.2705
Max Act: 3.9579. Min Act: -0.1700
Data Index: 1901232 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2705. Min Range: -4.2705
Max Act: 3.9579. Min Act: -0.1700
Data Index: 7422767 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2705. Min Range: -4.2705
Max Act: 3.9579. Min Act: -0.1700
Data Index: 1089669 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2705. Min Range: -4.2705
Max Act: 3.9267. Min Act: -0.1700
Data Index: 5505598 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2705. Min Range: -4.2705
Max Act: 3.9267. Min Act: -0.1700
Data Index: 2589939 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19