Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3581 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0138. Min Range: -6.0138
Max Act: 6.0138. Min Act: -0.1700
Data Index: 7474311 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0138. Min Range: -6.0138
Max Act: 5.9200. Min Act: -0.1700
Data Index: 5838849 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0138. Min Range: -6.0138
Max Act: 5.8575. Min Act: -0.1700
Data Index: 4007113 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0138. Min Range: -6.0138
Max Act: 5.8575. Min Act: -0.1700
Data Index: 1393420 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0138. Min Range: -6.0138
Max Act: 5.8263. Min Act: -0.1700
Data Index: 4293060 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0138. Min Range: -6.0138
Max Act: 5.8575. Min Act: -0.1700
Data Index: 2860796 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0138. Min Range: -6.0138
Max Act: 5.7950. Min Act: -0.1700
Data Index: 5139626 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0138. Min Range: -6.0138
Max Act: 5.7950. Min Act: -0.1700
Data Index: 7286403 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0138. Min Range: -6.0138
Max Act: 5.7638. Min Act: -0.1700
Data Index: 4181284 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0138. Min Range: -6.0138
Max Act: 5.7950. Min Act: -0.1700
Data Index: 7691540 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0138. Min Range: -6.0138
Max Act: 5.7325. Min Act: -0.1700
Data Index: 8247696 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0138. Min Range: -6.0138
Max Act: 5.7325. Min Act: -0.1700
Data Index: 3489129 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0138. Min Range: -6.0138
Max Act: 5.7325. Min Act: -0.1700
Data Index: 4842505 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0138. Min Range: -6.0138
Max Act: 5.7013. Min Act: -0.1700
Data Index: 1354018 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0138. Min Range: -6.0138
Max Act: 5.7013. Min Act: -0.1700
Data Index: 4339332 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0138. Min Range: -6.0138
Max Act: 5.6700. Min Act: -0.1700
Data Index: 4247168 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0138. Min Range: -6.0138
Max Act: 5.7013. Min Act: -0.1700
Data Index: 5229677 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0138. Min Range: -6.0138
Max Act: 5.6700. Min Act: -0.1700
Data Index: 2533377 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0138. Min Range: -6.0138
Max Act: 5.6700. Min Act: -0.1700
Data Index: 1204844 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0138. Min Range: -6.0138
Max Act: 5.6388. Min Act: -0.1700
Data Index: 6269465 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #19