Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4697 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 14.5986. Min Range: -14.5986
Max Act: 14.5986. Min Act: -0.1700
Data Index: 2883594 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.5986. Min Range: -14.5986
Max Act: 14.3486. Min Act: -0.1700
Data Index: 1543192 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.5986. Min Range: -14.5986
Max Act: 14.3486. Min Act: -0.1700
Data Index: 6760663 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.5986. Min Range: -14.5986
Max Act: 14.1611. Min Act: -0.1700
Data Index: 1660461 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.5986. Min Range: -14.5986
Max Act: 13.7236. Min Act: -0.1700
Data Index: 5451087 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.5986. Min Range: -14.5986
Max Act: 13.7236. Min Act: -0.1700
Data Index: 1834966 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.5986. Min Range: -14.5986
Max Act: 13.4736. Min Act: -0.1700
Data Index: 5454730 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.5986. Min Range: -14.5986
Max Act: 13.4736. Min Act: -0.1700
Data Index: 2257893 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.5986. Min Range: -14.5986
Max Act: 13.4736. Min Act: -0.1700
Data Index: 3283853 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.5986. Min Range: -14.5986
Max Act: 13.5361. Min Act: -0.1700
Data Index: 3117257 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.5986. Min Range: -14.5986
Max Act: 13.3486. Min Act: -0.1700
Data Index: 7009122 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.5986. Min Range: -14.5986
Max Act: 13.3486. Min Act: -0.1700
Data Index: 6190041 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.5986. Min Range: -14.5986
Max Act: 13.3486. Min Act: -0.1700
Data Index: 7400567 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.5986. Min Range: -14.5986
Max Act: 13.2861. Min Act: -0.1700
Data Index: 209641 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.5986. Min Range: -14.5986
Max Act: 13.2861. Min Act: -0.1700
Data Index: 3769416 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.5986. Min Range: -14.5986
Max Act: 13.2861. Min Act: -0.1700
Data Index: 6146488 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.5986. Min Range: -14.5986
Max Act: 13.2861. Min Act: -0.1700
Data Index: 5864770 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.5986. Min Range: -14.5986
Max Act: 13.2236. Min Act: -0.1700
Data Index: 3769234 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.5986. Min Range: -14.5986
Max Act: 13.2236. Min Act: -0.1700
Data Index: 6444379 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.5986. Min Range: -14.5986
Max Act: 13.1611. Min Act: -0.1700
Data Index: 3679867 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19