Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3999 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7376. Min Range: -6.7376
Max Act: 6.7376. Min Act: -0.1700
Data Index: 5377548 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7376. Min Range: -6.7376
Max Act: 6.5814. Min Act: -0.1700
Data Index: 6750394 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7376. Min Range: -6.7376
Max Act: 6.5501. Min Act: -0.1700
Data Index: 7080759 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7376. Min Range: -6.7376
Max Act: 6.4564. Min Act: -0.1700
Data Index: 4924818 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7376. Min Range: -6.7376
Max Act: 6.4251. Min Act: -0.1700
Data Index: 3652801 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7376. Min Range: -6.7376
Max Act: 6.3001. Min Act: -0.1700
Data Index: 630434 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7376. Min Range: -6.7376
Max Act: 6.2376. Min Act: -0.1700
Data Index: 787492 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7376. Min Range: -6.7376
Max Act: 6.1751. Min Act: -0.1700
Data Index: 2679954 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7376. Min Range: -6.7376
Max Act: 6.1751. Min Act: -0.1700
Data Index: 3240775 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7376. Min Range: -6.7376
Max Act: 6.1126. Min Act: -0.1700
Data Index: 1972889 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7376. Min Range: -6.7376
Max Act: 6.1126. Min Act: -0.1700
Data Index: 6194704 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7376. Min Range: -6.7376
Max Act: 6.1126. Min Act: -0.1700
Data Index: 255823 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7376. Min Range: -6.7376
Max Act: 6.0814. Min Act: -0.1700
Data Index: 2810896 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7376. Min Range: -6.7376
Max Act: 6.1126. Min Act: -0.1700
Data Index: 1914654 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7376. Min Range: -6.7376
Max Act: 6.1126. Min Act: -0.1700
Data Index: 6202551 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7376. Min Range: -6.7376
Max Act: 6.1439. Min Act: -0.1700
Data Index: 7519322 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7376. Min Range: -6.7376
Max Act: 6.0814. Min Act: -0.1700
Data Index: 6065972 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7376. Min Range: -6.7376
Max Act: 6.0814. Min Act: -0.1700
Data Index: 7272481 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7376. Min Range: -6.7376
Max Act: 6.0501. Min Act: -0.1700
Data Index: 3679184 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7376. Min Range: -6.7376
Max Act: 5.9876. Min Act: -0.1700
Data Index: 1941850 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19