Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3624 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8351. Min Range: -8.8351
Max Act: 8.8351. Min Act: -0.1700
Data Index: 1846274 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8351. Min Range: -8.8351
Max Act: 8.3351. Min Act: -0.1700
Data Index: 2513105 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8351. Min Range: -8.8351
Max Act: 8.3351. Min Act: -0.1700
Data Index: 8764693 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8351. Min Range: -8.8351
Max Act: 8.2726. Min Act: -0.1700
Data Index: 3924591 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8351. Min Range: -8.8351
Max Act: 8.0539. Min Act: -0.1700
Data Index: 3880727 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8351. Min Range: -8.8351
Max Act: 8.0539. Min Act: -0.1700
Data Index: 3137856 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8351. Min Range: -8.8351
Max Act: 7.9914. Min Act: -0.1700
Data Index: 545050 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8351. Min Range: -8.8351
Max Act: 7.9601. Min Act: -0.1700
Data Index: 4048409 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8351. Min Range: -8.8351
Max Act: 7.8976. Min Act: -0.1700
Data Index: 3636148 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8351. Min Range: -8.8351
Max Act: 7.8664. Min Act: -0.1700
Data Index: 5299089 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8351. Min Range: -8.8351
Max Act: 7.8039. Min Act: -0.1700
Data Index: 7322306 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8351. Min Range: -8.8351
Max Act: 7.8039. Min Act: -0.1700
Data Index: 4153120 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8351. Min Range: -8.8351
Max Act: 7.8039. Min Act: -0.1700
Data Index: 8454225 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8351. Min Range: -8.8351
Max Act: 7.7726. Min Act: -0.1700
Data Index: 8796640 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8351. Min Range: -8.8351
Max Act: 7.7414. Min Act: -0.1700
Data Index: 3838610 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8351. Min Range: -8.8351
Max Act: 7.7101. Min Act: -0.1700
Data Index: 7635166 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8351. Min Range: -8.8351
Max Act: 7.7101. Min Act: -0.1700
Data Index: 8386534 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8351. Min Range: -8.8351
Max Act: 7.6789. Min Act: -0.1700
Data Index: 7632687 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8351. Min Range: -8.8351
Max Act: 7.6476. Min Act: -0.1700
Data Index: 3829427 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8351. Min Range: -8.8351
Max Act: 7.6476. Min Act: -0.1700
Data Index: 5982591 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #19