Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3081 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6785. Min Range: -7.6785
Max Act: 7.6785. Min Act: -0.1700
Data Index: 2518703 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6785. Min Range: -7.6785
Max Act: 7.3972. Min Act: -0.1700
Data Index: 6430363 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6785. Min Range: -7.6785
Max Act: 7.3660. Min Act: -0.1700
Data Index: 3877453 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6785. Min Range: -7.6785
Max Act: 7.3972. Min Act: -0.1700
Data Index: 8637656 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6785. Min Range: -7.6785
Max Act: 7.3035. Min Act: -0.1700
Data Index: 5653655 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6785. Min Range: -7.6785
Max Act: 7.2410. Min Act: -0.1700
Data Index: 2910012 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6785. Min Range: -7.6785
Max Act: 7.2097. Min Act: -0.1700
Data Index: 339100 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6785. Min Range: -7.6785
Max Act: 7.1785. Min Act: -0.1700
Data Index: 6302033 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6785. Min Range: -7.6785
Max Act: 7.2097. Min Act: -0.1700
Data Index: 1577116 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6785. Min Range: -7.6785
Max Act: 7.1472. Min Act: -0.1700
Data Index: 278576 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6785. Min Range: -7.6785
Max Act: 7.1785. Min Act: -0.1700
Data Index: 58578 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6785. Min Range: -7.6785
Max Act: 7.1472. Min Act: -0.1700
Data Index: 4510665 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6785. Min Range: -7.6785
Max Act: 7.0535. Min Act: -0.1700
Data Index: 433803 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6785. Min Range: -7.6785
Max Act: 7.0222. Min Act: -0.1700
Data Index: 5976011 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6785. Min Range: -7.6785
Max Act: 7.0222. Min Act: -0.1700
Data Index: 608209 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6785. Min Range: -7.6785
Max Act: 7.0222. Min Act: -0.1700
Data Index: 4511273 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6785. Min Range: -7.6785
Max Act: 6.9597. Min Act: -0.1700
Data Index: 8386453 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6785. Min Range: -7.6785
Max Act: 7.0222. Min Act: -0.1700
Data Index: 617640 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6785. Min Range: -7.6785
Max Act: 6.9910. Min Act: -0.1700
Data Index: 1563616 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6785. Min Range: -7.6785
Max Act: 7.0222. Min Act: -0.1700
Data Index: 2910013 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #19