Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1628 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3426. Min Range: -5.3426
Max Act: 5.3426. Min Act: -0.1700
Data Index: 4950885 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3426. Min Range: -5.3426
Max Act: 5.3426. Min Act: -0.1700
Data Index: 2216532 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3426. Min Range: -5.3426
Max Act: 5.3114. Min Act: -0.1700
Data Index: 524956 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3426. Min Range: -5.3426
Max Act: 5.2801. Min Act: -0.1700
Data Index: 7825499 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3426. Min Range: -5.3426
Max Act: 5.1864. Min Act: -0.1700
Data Index: 3207566 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3426. Min Range: -5.3426
Max Act: 5.1551. Min Act: -0.1700
Data Index: 7114482 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3426. Min Range: -5.3426
Max Act: 5.0926. Min Act: -0.1700
Data Index: 693989 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3426. Min Range: -5.3426
Max Act: 5.0614. Min Act: -0.1700
Data Index: 4044763 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3426. Min Range: -5.3426
Max Act: 5.0614. Min Act: -0.1700
Data Index: 874130 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3426. Min Range: -5.3426
Max Act: 5.0926. Min Act: -0.1700
Data Index: 1642891 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3426. Min Range: -5.3426
Max Act: 5.0614. Min Act: -0.1700
Data Index: 1787612 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3426. Min Range: -5.3426
Max Act: 5.0301. Min Act: -0.1700
Data Index: 3322312 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3426. Min Range: -5.3426
Max Act: 5.0301. Min Act: -0.1700
Data Index: 8327032 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3426. Min Range: -5.3426
Max Act: 5.0301. Min Act: -0.1700
Data Index: 5954693 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3426. Min Range: -5.3426
Max Act: 5.0301. Min Act: -0.1700
Data Index: 6554666 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3426. Min Range: -5.3426
Max Act: 4.9676. Min Act: -0.1700
Data Index: 8008143 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3426. Min Range: -5.3426
Max Act: 4.9676. Min Act: -0.1700
Data Index: 782810 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3426. Min Range: -5.3426
Max Act: 4.9676. Min Act: -0.1700
Data Index: 3338191 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3426. Min Range: -5.3426
Max Act: 4.9364. Min Act: -0.1700
Data Index: 4417273 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3426. Min Range: -5.3426
Max Act: 4.9364. Min Act: -0.1700
Data Index: 7301580 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #19