Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2876 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1049. Min Range: -5.1049
Max Act: 5.1049. Min Act: -0.1700
Data Index: 3514636 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1049. Min Range: -5.1049
Max Act: 5.0112. Min Act: -0.1700
Data Index: 1455531 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1049. Min Range: -5.1049
Max Act: 5.0112. Min Act: -0.1700
Data Index: 5033354 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1049. Min Range: -5.1049
Max Act: 5.0112. Min Act: -0.1700
Data Index: 7262728 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1049. Min Range: -5.1049
Max Act: 5.0112. Min Act: -0.1700
Data Index: 78672 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1049. Min Range: -5.1049
Max Act: 4.9799. Min Act: -0.1700
Data Index: 7915906 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1049. Min Range: -5.1049
Max Act: 4.9799. Min Act: -0.1700
Data Index: 5091207 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1049. Min Range: -5.1049
Max Act: 4.9799. Min Act: -0.1700
Data Index: 2204415 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1049. Min Range: -5.1049
Max Act: 4.9799. Min Act: -0.1700
Data Index: 419271 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1049. Min Range: -5.1049
Max Act: 4.9799. Min Act: -0.1700
Data Index: 5596620 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1049. Min Range: -5.1049
Max Act: 4.9799. Min Act: -0.1700
Data Index: 4476150 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1049. Min Range: -5.1049
Max Act: 4.9487. Min Act: -0.1700
Data Index: 5135336 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1049. Min Range: -5.1049
Max Act: 4.9487. Min Act: -0.1700
Data Index: 2826227 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1049. Min Range: -5.1049
Max Act: 4.9487. Min Act: -0.1700
Data Index: 6295783 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1049. Min Range: -5.1049
Max Act: 4.9487. Min Act: -0.1700
Data Index: 3583580 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1049. Min Range: -5.1049
Max Act: 4.9487. Min Act: -0.1700
Data Index: 3995060 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1049. Min Range: -5.1049
Max Act: 4.9487. Min Act: -0.1700
Data Index: 4816429 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1049. Min Range: -5.1049
Max Act: 4.9487. Min Act: -0.1700
Data Index: 4176578 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1049. Min Range: -5.1049
Max Act: 4.9487. Min Act: -0.1700
Data Index: 4788804 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1049. Min Range: -5.1049
Max Act: 4.9487. Min Act: -0.1700
Data Index: 1661866 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #19