Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4885 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2375. Min Range: -9.2375
Max Act: 9.2375. Min Act: -0.1700
Data Index: 5233759 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2375. Min Range: -9.2375
Max Act: 8.8625. Min Act: -0.1700
Data Index: 6736175 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2375. Min Range: -9.2375
Max Act: 8.8625. Min Act: -0.1700
Data Index: 7968115 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2375. Min Range: -9.2375
Max Act: 8.9250. Min Act: -0.1700
Data Index: 1036423 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2375. Min Range: -9.2375
Max Act: 8.8000. Min Act: -0.1700
Data Index: 2771715 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2375. Min Range: -9.2375
Max Act: 8.6750. Min Act: -0.1700
Data Index: 4205845 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2375. Min Range: -9.2375
Max Act: 8.5500. Min Act: -0.1700
Data Index: 2876995 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2375. Min Range: -9.2375
Max Act: 8.4875. Min Act: -0.1700
Data Index: 2134000 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2375. Min Range: -9.2375
Max Act: 8.4250. Min Act: -0.1700
Data Index: 7288428 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2375. Min Range: -9.2375
Max Act: 8.3000. Min Act: -0.1700
Data Index: 7830008 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2375. Min Range: -9.2375
Max Act: 8.3625. Min Act: -0.1700
Data Index: 6036056 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2375. Min Range: -9.2375
Max Act: 8.3000. Min Act: -0.1700
Data Index: 5983925 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2375. Min Range: -9.2375
Max Act: 8.3000. Min Act: -0.1700
Data Index: 4681425 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2375. Min Range: -9.2375
Max Act: 8.3000. Min Act: -0.1700
Data Index: 5341985 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2375. Min Range: -9.2375
Max Act: 8.2375. Min Act: -0.1700
Data Index: 6323693 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2375. Min Range: -9.2375
Max Act: 8.2375. Min Act: -0.1700
Data Index: 3729097 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2375. Min Range: -9.2375
Max Act: 8.2375. Min Act: -0.1700
Data Index: 6458940 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2375. Min Range: -9.2375
Max Act: 8.1750. Min Act: -0.1700
Data Index: 3533193 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2375. Min Range: -9.2375
Max Act: 8.1125. Min Act: -0.1700
Data Index: 123377 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2375. Min Range: -9.2375
Max Act: 8.1750. Min Act: -0.1700
Data Index: 6941549 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #19