Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5790 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8587. Min Range: -5.8587
Max Act: 5.8587. Min Act: -0.1700
Data Index: 4052343 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8587. Min Range: -5.8587
Max Act: 5.8587. Min Act: -0.1700
Data Index: 961585 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8587. Min Range: -5.8587
Max Act: 5.8587. Min Act: -0.1700
Data Index: 52311 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8587. Min Range: -5.8587
Max Act: 5.8274. Min Act: -0.1700
Data Index: 2249577 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8587. Min Range: -5.8587
Max Act: 5.8274. Min Act: -0.1700
Data Index: 5382606 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8587. Min Range: -5.8587
Max Act: 5.7962. Min Act: -0.1700
Data Index: 5066620 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8587. Min Range: -5.8587
Max Act: 5.7649. Min Act: -0.1700
Data Index: 5731965 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8587. Min Range: -5.8587
Max Act: 5.7649. Min Act: -0.1700
Data Index: 3536817 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8587. Min Range: -5.8587
Max Act: 5.7337. Min Act: -0.1700
Data Index: 3792849 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8587. Min Range: -5.8587
Max Act: 5.7337. Min Act: -0.1700
Data Index: 4339902 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8587. Min Range: -5.8587
Max Act: 5.7024. Min Act: -0.1700
Data Index: 3814943 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8587. Min Range: -5.8587
Max Act: 5.7024. Min Act: -0.1700
Data Index: 5728785 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8587. Min Range: -5.8587
Max Act: 5.7024. Min Act: -0.1700
Data Index: 8069043 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8587. Min Range: -5.8587
Max Act: 5.6712. Min Act: -0.1700
Data Index: 4292973 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8587. Min Range: -5.8587
Max Act: 5.6399. Min Act: -0.1700
Data Index: 2002391 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8587. Min Range: -5.8587
Max Act: 5.6712. Min Act: -0.1700
Data Index: 6305200 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8587. Min Range: -5.8587
Max Act: 5.7024. Min Act: -0.1700
Data Index: 4721824 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8587. Min Range: -5.8587
Max Act: 5.6712. Min Act: -0.1700
Data Index: 5891610 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8587. Min Range: -5.8587
Max Act: 5.6712. Min Act: -0.1700
Data Index: 6783605 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8587. Min Range: -5.8587
Max Act: 5.6712. Min Act: -0.1700
Data Index: 7034130 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19