Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2940 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8597. Min Range: -3.8597
Max Act: 3.8597. Min Act: -0.1700
Data Index: 7826107 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8597. Min Range: -3.8597
Max Act: 3.8285. Min Act: -0.1700
Data Index: 4209850 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8597. Min Range: -3.8597
Max Act: 3.7346. Min Act: -0.1700
Data Index: 295519 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8597. Min Range: -3.8597
Max Act: 3.7033. Min Act: -0.1700
Data Index: 1143405 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8597. Min Range: -3.8597
Max Act: 3.6877. Min Act: -0.1700
Data Index: 7785752 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8597. Min Range: -3.8597
Max Act: 3.6721. Min Act: -0.1700
Data Index: 1916743 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8597. Min Range: -3.8597
Max Act: 3.6877. Min Act: -0.1700
Data Index: 3605994 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8597. Min Range: -3.8597
Max Act: 3.6408. Min Act: -0.1700
Data Index: 4786510 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8597. Min Range: -3.8597
Max Act: 3.6408. Min Act: -0.1700
Data Index: 2651175 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8597. Min Range: -3.8597
Max Act: 3.6408. Min Act: -0.1700
Data Index: 1838687 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8597. Min Range: -3.8597
Max Act: 3.6251. Min Act: -0.1700
Data Index: 103895 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8597. Min Range: -3.8597
Max Act: 3.6251. Min Act: -0.1700
Data Index: 6697608 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8597. Min Range: -3.8597
Max Act: 3.5938. Min Act: -0.1700
Data Index: 6159922 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8597. Min Range: -3.8597
Max Act: 3.5625. Min Act: -0.1700
Data Index: 6383117 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8597. Min Range: -3.8597
Max Act: 3.5782. Min Act: -0.1700
Data Index: 2662299 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8597. Min Range: -3.8597
Max Act: 3.5312. Min Act: -0.1700
Data Index: 1657365 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8597. Min Range: -3.8597
Max Act: 3.5312. Min Act: -0.1700
Data Index: 7765656 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8597. Min Range: -3.8597
Max Act: 3.5312. Min Act: -0.1700
Data Index: 1079853 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8597. Min Range: -3.8597
Max Act: 3.5312. Min Act: -0.1700
Data Index: 5122511 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8597. Min Range: -3.8597
Max Act: 3.5312. Min Act: -0.1700
Data Index: 8637585 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #19