Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4951 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3010. Min Range: -5.3010
Max Act: 5.3010. Min Act: -0.1700
Data Index: 5278522 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3010. Min Range: -5.3010
Max Act: 5.1760. Min Act: -0.1700
Data Index: 733006 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3010. Min Range: -5.3010
Max Act: 5.1447. Min Act: -0.1700
Data Index: 4239278 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3010. Min Range: -5.3010
Max Act: 5.1447. Min Act: -0.1700
Data Index: 2075707 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3010. Min Range: -5.3010
Max Act: 5.1447. Min Act: -0.1700
Data Index: 8166356 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3010. Min Range: -5.3010
Max Act: 5.1135. Min Act: -0.1700
Data Index: 303466 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3010. Min Range: -5.3010
Max Act: 5.0510. Min Act: -0.1700
Data Index: 802761 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3010. Min Range: -5.3010
Max Act: 5.0510. Min Act: -0.1700
Data Index: 4837398 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3010. Min Range: -5.3010
Max Act: 5.0510. Min Act: -0.1700
Data Index: 8445594 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3010. Min Range: -5.3010
Max Act: 5.0197. Min Act: -0.1700
Data Index: 8379396 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3010. Min Range: -5.3010
Max Act: 5.0510. Min Act: -0.1700
Data Index: 8275078 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3010. Min Range: -5.3010
Max Act: 5.0197. Min Act: -0.1700
Data Index: 8084402 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3010. Min Range: -5.3010
Max Act: 5.0197. Min Act: -0.1700
Data Index: 7701980 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3010. Min Range: -5.3010
Max Act: 5.0510. Min Act: -0.1700
Data Index: 4174196 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3010. Min Range: -5.3010
Max Act: 5.0197. Min Act: -0.1700
Data Index: 3984206 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3010. Min Range: -5.3010
Max Act: 5.0197. Min Act: -0.1700
Data Index: 2140436 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3010. Min Range: -5.3010
Max Act: 5.0197. Min Act: -0.1700
Data Index: 4079863 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3010. Min Range: -5.3010
Max Act: 5.0197. Min Act: -0.1700
Data Index: 4480736 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3010. Min Range: -5.3010
Max Act: 4.9885. Min Act: -0.1700
Data Index: 7178200 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3010. Min Range: -5.3010
Max Act: 5.0197. Min Act: -0.1700
Data Index: 757995 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #19