Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1378 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0765. Min Range: -6.0765
Max Act: 6.0765. Min Act: -0.1700
Data Index: 4705750 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0765. Min Range: -6.0765
Max Act: 5.8265. Min Act: -0.1700
Data Index: 2917424 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0765. Min Range: -6.0765
Max Act: 5.8265. Min Act: -0.1700
Data Index: 104702 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0765. Min Range: -6.0765
Max Act: 5.7640. Min Act: -0.1700
Data Index: 1947816 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0765. Min Range: -6.0765
Max Act: 5.7328. Min Act: -0.1700
Data Index: 4402500 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0765. Min Range: -6.0765
Max Act: 5.6703. Min Act: -0.1700
Data Index: 6728666 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0765. Min Range: -6.0765
Max Act: 5.6703. Min Act: -0.1700
Data Index: 2597083 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0765. Min Range: -6.0765
Max Act: 5.6390. Min Act: -0.1700
Data Index: 2502196 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0765. Min Range: -6.0765
Max Act: 5.6703. Min Act: -0.1700
Data Index: 1955267 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0765. Min Range: -6.0765
Max Act: 5.6390. Min Act: -0.1700
Data Index: 3841730 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0765. Min Range: -6.0765
Max Act: 5.6390. Min Act: -0.1700
Data Index: 1794705 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0765. Min Range: -6.0765
Max Act: 5.6390. Min Act: -0.1700
Data Index: 8486132 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0765. Min Range: -6.0765
Max Act: 5.6390. Min Act: -0.1700
Data Index: 2450705 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0765. Min Range: -6.0765
Max Act: 5.6390. Min Act: -0.1700
Data Index: 3134268 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0765. Min Range: -6.0765
Max Act: 5.6390. Min Act: -0.1700
Data Index: 6532427 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0765. Min Range: -6.0765
Max Act: 5.6078. Min Act: -0.1700
Data Index: 2731899 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0765. Min Range: -6.0765
Max Act: 5.6078. Min Act: -0.1700
Data Index: 1762842 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0765. Min Range: -6.0765
Max Act: 5.5453. Min Act: -0.1700
Data Index: 3414277 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0765. Min Range: -6.0765
Max Act: 5.5765. Min Act: -0.1700
Data Index: 635048 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0765. Min Range: -6.0765
Max Act: 5.5453. Min Act: -0.1700
Data Index: 5609444 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19