Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 103 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2914. Min Range: -4.2914
Max Act: 4.2914. Min Act: -0.1700
Data Index: 3874783 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2914. Min Range: -4.2914
Max Act: 4.0414. Min Act: -0.1700
Data Index: 3330805 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2914. Min Range: -4.2914
Max Act: 3.9789. Min Act: -0.1700
Data Index: 395270 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2914. Min Range: -4.2914
Max Act: 3.9163. Min Act: -0.1700
Data Index: 1035093 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2914. Min Range: -4.2914
Max Act: 3.9163. Min Act: -0.1700
Data Index: 1271927 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2914. Min Range: -4.2914
Max Act: 3.8851. Min Act: -0.1700
Data Index: 4604627 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2914. Min Range: -4.2914
Max Act: 3.8694. Min Act: -0.1700
Data Index: 7057893 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2914. Min Range: -4.2914
Max Act: 3.8694. Min Act: -0.1700
Data Index: 5598062 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2914. Min Range: -4.2914
Max Act: 3.8694. Min Act: -0.1700
Data Index: 2327654 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2914. Min Range: -4.2914
Max Act: 3.8538. Min Act: -0.1700
Data Index: 8814324 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2914. Min Range: -4.2914
Max Act: 3.8694. Min Act: -0.1700
Data Index: 4777059 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2914. Min Range: -4.2914
Max Act: 3.8694. Min Act: -0.1700
Data Index: 3527011 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2914. Min Range: -4.2914
Max Act: 3.8694. Min Act: -0.1700
Data Index: 1318809 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2914. Min Range: -4.2914
Max Act: 3.8538. Min Act: -0.1700
Data Index: 5088953 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2914. Min Range: -4.2914
Max Act: 3.8538. Min Act: -0.1700
Data Index: 6526100 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2914. Min Range: -4.2914
Max Act: 3.8069. Min Act: -0.1700
Data Index: 4437229 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2914. Min Range: -4.2914
Max Act: 3.8225. Min Act: -0.1700
Data Index: 1354009 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2914. Min Range: -4.2914
Max Act: 3.8069. Min Act: -0.1700
Data Index: 5785014 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2914. Min Range: -4.2914
Max Act: 3.8069. Min Act: -0.1700
Data Index: 1604007 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2914. Min Range: -4.2914
Max Act: 3.8069. Min Act: -0.1700
Data Index: 7442523 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19