Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1770 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6767. Min Range: -6.6767
Max Act: 6.6767. Min Act: -0.1700
Data Index: 18144 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6767. Min Range: -6.6767
Max Act: 6.6455. Min Act: -0.1700
Data Index: 4512425 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6767. Min Range: -6.6767
Max Act: 6.6142. Min Act: -0.1700
Data Index: 3372772 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6767. Min Range: -6.6767
Max Act: 6.6142. Min Act: -0.1700
Data Index: 808475 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6767. Min Range: -6.6767
Max Act: 6.5830. Min Act: -0.1700
Data Index: 8751656 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6767. Min Range: -6.6767
Max Act: 6.4267. Min Act: -0.1700
Data Index: 713973 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6767. Min Range: -6.6767
Max Act: 6.3955. Min Act: -0.1700
Data Index: 3258450 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6767. Min Range: -6.6767
Max Act: 6.3955. Min Act: -0.1700
Data Index: 7460480 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6767. Min Range: -6.6767
Max Act: 6.4267. Min Act: -0.1700
Data Index: 5729054 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6767. Min Range: -6.6767
Max Act: 6.3955. Min Act: -0.1700
Data Index: 916504 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6767. Min Range: -6.6767
Max Act: 6.3955. Min Act: -0.1700
Data Index: 8591743 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6767. Min Range: -6.6767
Max Act: 6.4267. Min Act: -0.1700
Data Index: 8740860 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6767. Min Range: -6.6767
Max Act: 6.3330. Min Act: -0.1700
Data Index: 1447395 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6767. Min Range: -6.6767
Max Act: 6.3642. Min Act: -0.1700
Data Index: 236541 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6767. Min Range: -6.6767
Max Act: 6.3642. Min Act: -0.1700
Data Index: 5623206 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6767. Min Range: -6.6767
Max Act: 6.3642. Min Act: -0.1700
Data Index: 7855197 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6767. Min Range: -6.6767
Max Act: 6.3642. Min Act: -0.1700
Data Index: 4928594 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6767. Min Range: -6.6767
Max Act: 6.3017. Min Act: -0.1700
Data Index: 642178 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6767. Min Range: -6.6767
Max Act: 6.2705. Min Act: -0.1700
Data Index: 3258741 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6767. Min Range: -6.6767
Max Act: 6.3017. Min Act: -0.1700
Data Index: 6572950 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #19