Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4594 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6104. Min Range: -8.6104
Max Act: 8.6104. Min Act: -0.1700
Data Index: 3209479 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6104. Min Range: -8.6104
Max Act: 8.2354. Min Act: -0.1700
Data Index: 1323978 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6104. Min Range: -8.6104
Max Act: 8.1729. Min Act: -0.1700
Data Index: 431341 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6104. Min Range: -8.6104
Max Act: 8.1104. Min Act: -0.1700
Data Index: 7058870 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6104. Min Range: -8.6104
Max Act: 8.0479. Min Act: -0.1700
Data Index: 7179648 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6104. Min Range: -8.6104
Max Act: 7.9854. Min Act: -0.1700
Data Index: 7355341 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6104. Min Range: -8.6104
Max Act: 7.9229. Min Act: -0.1700
Data Index: 6309696 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6104. Min Range: -8.6104
Max Act: 7.9229. Min Act: -0.1700
Data Index: 7867740 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6104. Min Range: -8.6104
Max Act: 7.8604. Min Act: -0.1700
Data Index: 1617500 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6104. Min Range: -8.6104
Max Act: 7.8604. Min Act: -0.1700
Data Index: 3786724 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6104. Min Range: -8.6104
Max Act: 7.7979. Min Act: -0.1700
Data Index: 5504297 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6104. Min Range: -8.6104
Max Act: 7.7354. Min Act: -0.1700
Data Index: 2271018 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6104. Min Range: -8.6104
Max Act: 7.7354. Min Act: -0.1700
Data Index: 3675206 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6104. Min Range: -8.6104
Max Act: 7.7354. Min Act: -0.1700
Data Index: 4727991 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6104. Min Range: -8.6104
Max Act: 7.6729. Min Act: -0.1700
Data Index: 4256235 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6104. Min Range: -8.6104
Max Act: 7.6729. Min Act: -0.1700
Data Index: 1207285 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6104. Min Range: -8.6104
Max Act: 7.6416. Min Act: -0.1700
Data Index: 7579911 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6104. Min Range: -8.6104
Max Act: 7.6729. Min Act: -0.1700
Data Index: 2865613 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6104. Min Range: -8.6104
Max Act: 7.6416. Min Act: -0.1700
Data Index: 1775071 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6104. Min Range: -8.6104
Max Act: 7.6104. Min Act: -0.1700
Data Index: 7983443 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #19