Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3660 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6523. Min Range: -4.6523
Max Act: 4.6523. Min Act: -0.1700
Data Index: 605871 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6523. Min Range: -4.6523
Max Act: 4.5585. Min Act: -0.1700
Data Index: 4934254 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6523. Min Range: -4.6523
Max Act: 4.5585. Min Act: -0.1700
Data Index: 1617261 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6523. Min Range: -4.6523
Max Act: 4.5585. Min Act: -0.1700
Data Index: 1059313 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6523. Min Range: -4.6523
Max Act: 4.5273. Min Act: -0.1700
Data Index: 2642102 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6523. Min Range: -4.6523
Max Act: 4.4960. Min Act: -0.1700
Data Index: 2816739 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6523. Min Range: -4.6523
Max Act: 4.4960. Min Act: -0.1700
Data Index: 3815861 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6523. Min Range: -4.6523
Max Act: 4.4648. Min Act: -0.1700
Data Index: 8617142 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6523. Min Range: -4.6523
Max Act: 4.4648. Min Act: -0.1700
Data Index: 1741111 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6523. Min Range: -4.6523
Max Act: 4.4648. Min Act: -0.1700
Data Index: 1290093 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6523. Min Range: -4.6523
Max Act: 4.4648. Min Act: -0.1700
Data Index: 4952895 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6523. Min Range: -4.6523
Max Act: 4.4648. Min Act: -0.1700
Data Index: 8778508 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6523. Min Range: -4.6523
Max Act: 4.4960. Min Act: -0.1700
Data Index: 1654099 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6523. Min Range: -4.6523
Max Act: 4.4335. Min Act: -0.1700
Data Index: 3546800 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6523. Min Range: -4.6523
Max Act: 4.4335. Min Act: -0.1700
Data Index: 8144087 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6523. Min Range: -4.6523
Max Act: 4.4335. Min Act: -0.1700
Data Index: 8263787 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6523. Min Range: -4.6523
Max Act: 4.4335. Min Act: -0.1700
Data Index: 620486 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6523. Min Range: -4.6523
Max Act: 4.4023. Min Act: -0.1700
Data Index: 5378882 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6523. Min Range: -4.6523
Max Act: 4.4023. Min Act: -0.1700
Data Index: 8517238 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6523. Min Range: -4.6523
Max Act: 4.4023. Min Act: -0.1700
Data Index: 4115271 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #19