Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6378 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 20.4872. Min Range: -20.4872
Max Act: 20.4872. Min Act: -0.1700
Data Index: 4677016 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 20.4872. Min Range: -20.4872
Max Act: 20.3622. Min Act: -0.1700
Data Index: 7434126 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 20.4872. Min Range: -20.4872
Max Act: 19.4872. Min Act: -0.1700
Data Index: 8380985 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 20.4872. Min Range: -20.4872
Max Act: 19.2372. Min Act: -0.1700
Data Index: 7187561 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 20.4872. Min Range: -20.4872
Max Act: 19.1122. Min Act: -0.1700
Data Index: 8494489 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 20.4872. Min Range: -20.4872
Max Act: 18.8622. Min Act: -0.1700
Data Index: 5399241 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 20.4872. Min Range: -20.4872
Max Act: 18.8622. Min Act: -0.1700
Data Index: 8295554 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 20.4872. Min Range: -20.4872
Max Act: 18.6122. Min Act: -0.1700
Data Index: 2849285 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 20.4872. Min Range: -20.4872
Max Act: 18.4872. Min Act: -0.1700
Data Index: 7174355 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 20.4872. Min Range: -20.4872
Max Act: 18.4872. Min Act: -0.1700
Data Index: 6296885 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 20.4872. Min Range: -20.4872
Max Act: 18.4872. Min Act: -0.1700
Data Index: 1738918 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 20.4872. Min Range: -20.4872
Max Act: 18.3622. Min Act: -0.1700
Data Index: 8015856 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 20.4872. Min Range: -20.4872
Max Act: 18.3622. Min Act: -0.1700
Data Index: 5320882 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 20.4872. Min Range: -20.4872
Max Act: 17.9872. Min Act: -0.1700
Data Index: 7730094 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 20.4872. Min Range: -20.4872
Max Act: 17.9872. Min Act: -0.1700
Data Index: 1935969 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 20.4872. Min Range: -20.4872
Max Act: 17.8622. Min Act: -0.1700
Data Index: 1061492 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 20.4872. Min Range: -20.4872
Max Act: 17.8622. Min Act: -0.1700
Data Index: 777976 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 20.4872. Min Range: -20.4872
Max Act: 17.8622. Min Act: -0.1700
Data Index: 8550221 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 20.4872. Min Range: -20.4872
Max Act: 17.8622. Min Act: -0.1700
Data Index: 5477865 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 20.4872. Min Range: -20.4872
Max Act: 17.7372. Min Act: -0.1700
Data Index: 7370486 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #19