Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3471 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5400. Min Range: -6.5400
Max Act: 6.5400. Min Act: -0.1700
Data Index: 2395113 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5400. Min Range: -6.5400
Max Act: 6.1338. Min Act: -0.1700
Data Index: 506972 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5400. Min Range: -6.5400
Max Act: 6.1025. Min Act: -0.1700
Data Index: 3693286 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5400. Min Range: -6.5400
Max Act: 6.1025. Min Act: -0.1700
Data Index: 2602833 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5400. Min Range: -6.5400
Max Act: 6.0713. Min Act: -0.1700
Data Index: 7137192 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5400. Min Range: -6.5400
Max Act: 6.1025. Min Act: -0.1700
Data Index: 7898533 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5400. Min Range: -6.5400
Max Act: 6.0400. Min Act: -0.1700
Data Index: 4940552 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5400. Min Range: -6.5400
Max Act: 6.0400. Min Act: -0.1700
Data Index: 6134998 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5400. Min Range: -6.5400
Max Act: 6.0400. Min Act: -0.1700
Data Index: 5262749 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5400. Min Range: -6.5400
Max Act: 6.0713. Min Act: -0.1700
Data Index: 7583369 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5400. Min Range: -6.5400
Max Act: 6.0088. Min Act: -0.1700
Data Index: 5942674 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5400. Min Range: -6.5400
Max Act: 5.9463. Min Act: -0.1700
Data Index: 4513267 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5400. Min Range: -6.5400
Max Act: 5.9463. Min Act: -0.1700
Data Index: 6946720 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5400. Min Range: -6.5400
Max Act: 5.9463. Min Act: -0.1700
Data Index: 1395362 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5400. Min Range: -6.5400
Max Act: 5.9150. Min Act: -0.1700
Data Index: 6119272 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5400. Min Range: -6.5400
Max Act: 5.8838. Min Act: -0.1700
Data Index: 2103699 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5400. Min Range: -6.5400
Max Act: 5.9150. Min Act: -0.1700
Data Index: 6843227 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5400. Min Range: -6.5400
Max Act: 5.8838. Min Act: -0.1700
Data Index: 6127894 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5400. Min Range: -6.5400
Max Act: 5.8525. Min Act: -0.1700
Data Index: 4775396 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5400. Min Range: -6.5400
Max Act: 5.8525. Min Act: -0.1700
Data Index: 3086897 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19