Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3773 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9453. Min Range: -5.9453
Max Act: 5.9453. Min Act: -0.1700
Data Index: 605780 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9453. Min Range: -5.9453
Max Act: 5.8515. Min Act: -0.1700
Data Index: 3257912 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9453. Min Range: -5.9453
Max Act: 5.7890. Min Act: -0.1700
Data Index: 98432 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9453. Min Range: -5.9453
Max Act: 5.7578. Min Act: -0.1700
Data Index: 4806174 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9453. Min Range: -5.9453
Max Act: 5.7578. Min Act: -0.1700
Data Index: 900670 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9453. Min Range: -5.9453
Max Act: 5.7265. Min Act: -0.1700
Data Index: 6239371 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9453. Min Range: -5.9453
Max Act: 5.6640. Min Act: -0.1700
Data Index: 967316 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9453. Min Range: -5.9453
Max Act: 5.6328. Min Act: -0.1700
Data Index: 7905975 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9453. Min Range: -5.9453
Max Act: 5.6328. Min Act: -0.1700
Data Index: 2156053 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9453. Min Range: -5.9453
Max Act: 5.6953. Min Act: -0.1700
Data Index: 1157662 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9453. Min Range: -5.9453
Max Act: 5.6328. Min Act: -0.1700
Data Index: 3418024 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9453. Min Range: -5.9453
Max Act: 5.6015. Min Act: -0.1700
Data Index: 2448368 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9453. Min Range: -5.9453
Max Act: 5.6328. Min Act: -0.1700
Data Index: 3466506 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9453. Min Range: -5.9453
Max Act: 5.6015. Min Act: -0.1700
Data Index: 4565205 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9453. Min Range: -5.9453
Max Act: 5.5703. Min Act: -0.1700
Data Index: 6173338 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9453. Min Range: -5.9453
Max Act: 5.6015. Min Act: -0.1700
Data Index: 2155330 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9453. Min Range: -5.9453
Max Act: 5.5390. Min Act: -0.1700
Data Index: 3280403 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9453. Min Range: -5.9453
Max Act: 5.5390. Min Act: -0.1700
Data Index: 8248470 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9453. Min Range: -5.9453
Max Act: 5.5078. Min Act: -0.1700
Data Index: 3509332 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9453. Min Range: -5.9453
Max Act: 5.5078. Min Act: -0.1700
Data Index: 5926648 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #19