Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1616 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5592. Min Range: -4.5592
Max Act: 4.5592. Min Act: -0.1700
Data Index: 8415510 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5592. Min Range: -4.5592
Max Act: 4.4342. Min Act: -0.1700
Data Index: 3771724 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5592. Min Range: -4.5592
Max Act: 4.3405. Min Act: -0.1700
Data Index: 3098887 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5592. Min Range: -4.5592
Max Act: 4.2780. Min Act: -0.1700
Data Index: 4783714 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5592. Min Range: -4.5592
Max Act: 4.2780. Min Act: -0.1700
Data Index: 2718840 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5592. Min Range: -4.5592
Max Act: 4.2467. Min Act: -0.1700
Data Index: 8720394 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5592. Min Range: -4.5592
Max Act: 4.2155. Min Act: -0.1700
Data Index: 8419219 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5592. Min Range: -4.5592
Max Act: 4.1530. Min Act: -0.1700
Data Index: 6644401 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5592. Min Range: -4.5592
Max Act: 4.1530. Min Act: -0.1700
Data Index: 5659360 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5592. Min Range: -4.5592
Max Act: 4.1530. Min Act: -0.1700
Data Index: 2940997 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5592. Min Range: -4.5592
Max Act: 4.1530. Min Act: -0.1700
Data Index: 3948076 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5592. Min Range: -4.5592
Max Act: 4.1530. Min Act: -0.1700
Data Index: 6017576 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5592. Min Range: -4.5592
Max Act: 4.1530. Min Act: -0.1700
Data Index: 6400713 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5592. Min Range: -4.5592
Max Act: 4.1217. Min Act: -0.1700
Data Index: 2687318 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5592. Min Range: -4.5592
Max Act: 4.1530. Min Act: -0.1700
Data Index: 1462978 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5592. Min Range: -4.5592
Max Act: 4.0904. Min Act: -0.1700
Data Index: 896115 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5592. Min Range: -4.5592
Max Act: 4.0904. Min Act: -0.1700
Data Index: 6303571 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5592. Min Range: -4.5592
Max Act: 4.0592. Min Act: -0.1700
Data Index: 7733556 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5592. Min Range: -4.5592
Max Act: 4.0904. Min Act: -0.1700
Data Index: 6527874 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5592. Min Range: -4.5592
Max Act: 4.0904. Min Act: -0.1700
Data Index: 6166456 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #19