Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3467 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8721. Min Range: -4.8721
Max Act: 4.8721. Min Act: -0.1700
Data Index: 1234122 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8721. Min Range: -4.8721
Max Act: 4.6533. Min Act: -0.1700
Data Index: 4709740 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8721. Min Range: -4.8721
Max Act: 4.6221. Min Act: -0.1700
Data Index: 2427454 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8721. Min Range: -4.8721
Max Act: 4.5908. Min Act: -0.1700
Data Index: 5300225 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8721. Min Range: -4.8721
Max Act: 4.4971. Min Act: -0.1700
Data Index: 3548162 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8721. Min Range: -4.8721
Max Act: 4.4658. Min Act: -0.1700
Data Index: 5893514 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8721. Min Range: -4.8721
Max Act: 4.4345. Min Act: -0.1700
Data Index: 5838560 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8721. Min Range: -4.8721
Max Act: 4.4345. Min Act: -0.1700
Data Index: 1809771 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8721. Min Range: -4.8721
Max Act: 4.4345. Min Act: -0.1700
Data Index: 8258011 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8721. Min Range: -4.8721
Max Act: 4.4033. Min Act: -0.1700
Data Index: 2666042 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8721. Min Range: -4.8721
Max Act: 4.3720. Min Act: -0.1700
Data Index: 8589985 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8721. Min Range: -4.8721
Max Act: 4.3720. Min Act: -0.1700
Data Index: 7014111 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8721. Min Range: -4.8721
Max Act: 4.3720. Min Act: -0.1700
Data Index: 6858594 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8721. Min Range: -4.8721
Max Act: 4.3720. Min Act: -0.1700
Data Index: 150109 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8721. Min Range: -4.8721
Max Act: 4.3720. Min Act: -0.1700
Data Index: 8193681 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8721. Min Range: -4.8721
Max Act: 4.3408. Min Act: -0.1700
Data Index: 2658465 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8721. Min Range: -4.8721
Max Act: 4.3720. Min Act: -0.1700
Data Index: 8526987 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8721. Min Range: -4.8721
Max Act: 4.3408. Min Act: -0.1700
Data Index: 6849632 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8721. Min Range: -4.8721
Max Act: 4.3095. Min Act: -0.1700
Data Index: 3664251 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8721. Min Range: -4.8721
Max Act: 4.3408. Min Act: -0.1700
Data Index: 4461333 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #19