Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 664 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1742. Min Range: -4.1742
Max Act: 4.1742. Min Act: -0.1700
Data Index: 6825347 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1742. Min Range: -4.1742
Max Act: 3.9241. Min Act: -0.1700
Data Index: 2242074 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1742. Min Range: -4.1742
Max Act: 3.8929. Min Act: -0.1700
Data Index: 321326 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1742. Min Range: -4.1742
Max Act: 3.8772. Min Act: -0.1700
Data Index: 1926689 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1742. Min Range: -4.1742
Max Act: 3.9085. Min Act: -0.1700
Data Index: 5968853 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1742. Min Range: -4.1742
Max Act: 3.8147. Min Act: -0.1700
Data Index: 8793582 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1742. Min Range: -4.1742
Max Act: 3.7990. Min Act: -0.1700
Data Index: 7899323 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1742. Min Range: -4.1742
Max Act: 3.7834. Min Act: -0.1700
Data Index: 1772576 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1742. Min Range: -4.1742
Max Act: 3.7834. Min Act: -0.1700
Data Index: 4407395 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1742. Min Range: -4.1742
Max Act: 3.7365. Min Act: -0.1700
Data Index: 4273828 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1742. Min Range: -4.1742
Max Act: 3.7365. Min Act: -0.1700
Data Index: 7221254 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1742. Min Range: -4.1742
Max Act: 3.7365. Min Act: -0.1700
Data Index: 5553328 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1742. Min Range: -4.1742
Max Act: 3.7052. Min Act: -0.1700
Data Index: 3775516 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1742. Min Range: -4.1742
Max Act: 3.7052. Min Act: -0.1700
Data Index: 2696830 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1742. Min Range: -4.1742
Max Act: 3.6896. Min Act: -0.1700
Data Index: 8379689 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1742. Min Range: -4.1742
Max Act: 3.7052. Min Act: -0.1700
Data Index: 5534411 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1742. Min Range: -4.1742
Max Act: 3.7052. Min Act: -0.1700
Data Index: 1904815 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1742. Min Range: -4.1742
Max Act: 3.6896. Min Act: -0.1700
Data Index: 8625218 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1742. Min Range: -4.1742
Max Act: 3.6583. Min Act: -0.1700
Data Index: 8600547 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1742. Min Range: -4.1742
Max Act: 3.6896. Min Act: -0.1700
Data Index: 2515472 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #19