Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2757 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6481. Min Range: -8.6481
Max Act: 8.6481. Min Act: -0.1700
Data Index: 3009746 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6481. Min Range: -8.6481
Max Act: 8.3356. Min Act: -0.1700
Data Index: 5093167 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6481. Min Range: -8.6481
Max Act: 8.2106. Min Act: -0.1700
Data Index: 8679296 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6481. Min Range: -8.6481
Max Act: 8.2106. Min Act: -0.1700
Data Index: 5214259 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6481. Min Range: -8.6481
Max Act: 8.0543. Min Act: -0.1700
Data Index: 8785465 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6481. Min Range: -8.6481
Max Act: 8.0231. Min Act: -0.1700
Data Index: 7180437 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6481. Min Range: -8.6481
Max Act: 8.0856. Min Act: -0.1700
Data Index: 3821420 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6481. Min Range: -8.6481
Max Act: 7.9918. Min Act: -0.1700
Data Index: 2064621 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6481. Min Range: -8.6481
Max Act: 7.9606. Min Act: -0.1700
Data Index: 8219799 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6481. Min Range: -8.6481
Max Act: 7.9606. Min Act: -0.1700
Data Index: 1655700 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6481. Min Range: -8.6481
Max Act: 7.9293. Min Act: -0.1700
Data Index: 3181842 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6481. Min Range: -8.6481
Max Act: 7.8981. Min Act: -0.1700
Data Index: 7255552 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6481. Min Range: -8.6481
Max Act: 7.8981. Min Act: -0.1700
Data Index: 889227 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6481. Min Range: -8.6481
Max Act: 7.8668. Min Act: -0.1700
Data Index: 2981521 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6481. Min Range: -8.6481
Max Act: 7.8356. Min Act: -0.1700
Data Index: 1870652 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6481. Min Range: -8.6481
Max Act: 7.8356. Min Act: -0.1700
Data Index: 1815728 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6481. Min Range: -8.6481
Max Act: 7.8043. Min Act: -0.1700
Data Index: 5760276 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6481. Min Range: -8.6481
Max Act: 7.7731. Min Act: -0.1700
Data Index: 7896044 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6481. Min Range: -8.6481
Max Act: 7.7418. Min Act: -0.1700
Data Index: 6814127 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6481. Min Range: -8.6481
Max Act: 7.7731. Min Act: -0.1700
Data Index: 8663479 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19