Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2561 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4790. Min Range: -8.4790
Max Act: 8.4790. Min Act: -0.1700
Data Index: 3344477 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4790. Min Range: -8.4790
Max Act: 8.4165. Min Act: -0.1700
Data Index: 8108947 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4790. Min Range: -8.4790
Max Act: 7.9790. Min Act: -0.1700
Data Index: 8176116 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4790. Min Range: -8.4790
Max Act: 7.9165. Min Act: -0.1700
Data Index: 1950385 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4790. Min Range: -8.4790
Max Act: 7.7602. Min Act: -0.1700
Data Index: 6220425 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4790. Min Range: -8.4790
Max Act: 7.7602. Min Act: -0.1700
Data Index: 457398 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4790. Min Range: -8.4790
Max Act: 7.6977. Min Act: -0.1700
Data Index: 6826305 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4790. Min Range: -8.4790
Max Act: 7.6977. Min Act: -0.1700
Data Index: 8121337 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4790. Min Range: -8.4790
Max Act: 7.6665. Min Act: -0.1700
Data Index: 6432151 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4790. Min Range: -8.4790
Max Act: 7.6352. Min Act: -0.1700
Data Index: 5074861 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4790. Min Range: -8.4790
Max Act: 7.6040. Min Act: -0.1700
Data Index: 1720906 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4790. Min Range: -8.4790
Max Act: 7.5415. Min Act: -0.1700
Data Index: 3067587 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4790. Min Range: -8.4790
Max Act: 7.5415. Min Act: -0.1700
Data Index: 5543319 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4790. Min Range: -8.4790
Max Act: 7.5102. Min Act: -0.1700
Data Index: 6415441 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4790. Min Range: -8.4790
Max Act: 7.5102. Min Act: -0.1700
Data Index: 5291406 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4790. Min Range: -8.4790
Max Act: 7.5102. Min Act: -0.1700
Data Index: 6660140 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4790. Min Range: -8.4790
Max Act: 7.5415. Min Act: -0.1700
Data Index: 1471655 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4790. Min Range: -8.4790
Max Act: 7.5102. Min Act: -0.1700
Data Index: 6009615 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4790. Min Range: -8.4790
Max Act: 7.4790. Min Act: -0.1700
Data Index: 1274971 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4790. Min Range: -8.4790
Max Act: 7.4790. Min Act: -0.1700
Data Index: 3356072 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #19