Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6063 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0494. Min Range: -6.0494
Max Act: 6.0494. Min Act: -0.1700
Data Index: 1750368 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0494. Min Range: -6.0494
Max Act: 5.9556. Min Act: -0.1700
Data Index: 64171 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0494. Min Range: -6.0494
Max Act: 5.9244. Min Act: -0.1700
Data Index: 1425230 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0494. Min Range: -6.0494
Max Act: 5.9244. Min Act: -0.1700
Data Index: 6684610 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0494. Min Range: -6.0494
Max Act: 5.9244. Min Act: -0.1700
Data Index: 6266470 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0494. Min Range: -6.0494
Max Act: 5.9244. Min Act: -0.1700
Data Index: 6719951 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0494. Min Range: -6.0494
Max Act: 5.8931. Min Act: -0.1700
Data Index: 6564693 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0494. Min Range: -6.0494
Max Act: 5.8931. Min Act: -0.1700
Data Index: 2896052 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0494. Min Range: -6.0494
Max Act: 5.8931. Min Act: -0.1700
Data Index: 6110791 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0494. Min Range: -6.0494
Max Act: 5.8619. Min Act: -0.1700
Data Index: 5458806 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0494. Min Range: -6.0494
Max Act: 5.8619. Min Act: -0.1700
Data Index: 4701357 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0494. Min Range: -6.0494
Max Act: 5.8619. Min Act: -0.1700
Data Index: 3368867 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0494. Min Range: -6.0494
Max Act: 5.8619. Min Act: -0.1700
Data Index: 1643455 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0494. Min Range: -6.0494
Max Act: 5.8619. Min Act: -0.1700
Data Index: 6025834 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0494. Min Range: -6.0494
Max Act: 5.8619. Min Act: -0.1700
Data Index: 577707 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0494. Min Range: -6.0494
Max Act: 5.8619. Min Act: -0.1700
Data Index: 5620057 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0494. Min Range: -6.0494
Max Act: 5.8306. Min Act: -0.1700
Data Index: 4243464 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0494. Min Range: -6.0494
Max Act: 5.8306. Min Act: -0.1700
Data Index: 463696 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0494. Min Range: -6.0494
Max Act: 5.8306. Min Act: -0.1700
Data Index: 4741810 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0494. Min Range: -6.0494
Max Act: 5.8306. Min Act: -0.1700
Data Index: 3600572 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #19