Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2638 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8021. Min Range: -5.8021
Max Act: 5.8021. Min Act: -0.1700
Data Index: 6860227 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8021. Min Range: -5.8021
Max Act: 5.4896. Min Act: -0.1700
Data Index: 6494279 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8021. Min Range: -5.8021
Max Act: 5.4583. Min Act: -0.1700
Data Index: 4544841 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8021. Min Range: -5.8021
Max Act: 5.3021. Min Act: -0.1700
Data Index: 6023587 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8021. Min Range: -5.8021
Max Act: 5.3021. Min Act: -0.1700
Data Index: 6574317 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8021. Min Range: -5.8021
Max Act: 5.3021. Min Act: -0.1700
Data Index: 5059748 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8021. Min Range: -5.8021
Max Act: 5.3021. Min Act: -0.1700
Data Index: 6112918 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8021. Min Range: -5.8021
Max Act: 5.1771. Min Act: -0.1700
Data Index: 6442738 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8021. Min Range: -5.8021
Max Act: 5.1771. Min Act: -0.1700
Data Index: 2561441 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8021. Min Range: -5.8021
Max Act: 5.1458. Min Act: -0.1700
Data Index: 525505 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8021. Min Range: -5.8021
Max Act: 5.1458. Min Act: -0.1700
Data Index: 6463447 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8021. Min Range: -5.8021
Max Act: 5.1771. Min Act: -0.1700
Data Index: 4544126 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8021. Min Range: -5.8021
Max Act: 5.1146. Min Act: -0.1700
Data Index: 5649461 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8021. Min Range: -5.8021
Max Act: 5.1146. Min Act: -0.1700
Data Index: 8732494 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8021. Min Range: -5.8021
Max Act: 5.0521. Min Act: -0.1700
Data Index: 2989266 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8021. Min Range: -5.8021
Max Act: 5.0208. Min Act: -0.1700
Data Index: 4694952 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8021. Min Range: -5.8021
Max Act: 5.0521. Min Act: -0.1700
Data Index: 2471239 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8021. Min Range: -5.8021
Max Act: 5.0521. Min Act: -0.1700
Data Index: 12716 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8021. Min Range: -5.8021
Max Act: 5.0208. Min Act: -0.1700
Data Index: 5956710 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8021. Min Range: -5.8021
Max Act: 4.9896. Min Act: -0.1700
Data Index: 4731298 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19