Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4704 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7218. Min Range: -5.7218
Max Act: 5.7218. Min Act: -0.1700
Data Index: 8805377 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7218. Min Range: -5.7218
Max Act: 5.1593. Min Act: -0.1700
Data Index: 5760940 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7218. Min Range: -5.7218
Max Act: 5.1280. Min Act: -0.1700
Data Index: 8578379 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7218. Min Range: -5.7218
Max Act: 5.0968. Min Act: -0.1700
Data Index: 4476515 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7218. Min Range: -5.7218
Max Act: 5.0655. Min Act: -0.1700
Data Index: 8246136 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7218. Min Range: -5.7218
Max Act: 5.0343. Min Act: -0.1700
Data Index: 7205892 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7218. Min Range: -5.7218
Max Act: 5.0655. Min Act: -0.1700
Data Index: 504892 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7218. Min Range: -5.7218
Max Act: 5.0655. Min Act: -0.1700
Data Index: 816190 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7218. Min Range: -5.7218
Max Act: 5.0655. Min Act: -0.1700
Data Index: 3206707 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7218. Min Range: -5.7218
Max Act: 5.0343. Min Act: -0.1700
Data Index: 6413011 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7218. Min Range: -5.7218
Max Act: 5.0030. Min Act: -0.1700
Data Index: 8501257 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7218. Min Range: -5.7218
Max Act: 5.0030. Min Act: -0.1700
Data Index: 1118038 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7218. Min Range: -5.7218
Max Act: 4.9718. Min Act: -0.1700
Data Index: 2665090 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7218. Min Range: -5.7218
Max Act: 4.9718. Min Act: -0.1700
Data Index: 6252456 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7218. Min Range: -5.7218
Max Act: 4.9718. Min Act: -0.1700
Data Index: 8246492 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7218. Min Range: -5.7218
Max Act: 4.9718. Min Act: -0.1700
Data Index: 1095847 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7218. Min Range: -5.7218
Max Act: 4.9405. Min Act: -0.1700
Data Index: 420052 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7218. Min Range: -5.7218
Max Act: 4.9093. Min Act: -0.1700
Data Index: 5241981 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7218. Min Range: -5.7218
Max Act: 4.9093. Min Act: -0.1700
Data Index: 3174573 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7218. Min Range: -5.7218
Max Act: 4.9093. Min Act: -0.1700
Data Index: 3974540 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19