Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3409 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2534. Min Range: -5.2534
Max Act: 5.2534. Min Act: -0.1700
Data Index: 4039371 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2534. Min Range: -5.2534
Max Act: 5.2221. Min Act: -0.1700
Data Index: 6106147 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2534. Min Range: -5.2534
Max Act: 5.1909. Min Act: -0.1700
Data Index: 3377325 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2534. Min Range: -5.2534
Max Act: 5.1596. Min Act: -0.1700
Data Index: 8435095 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2534. Min Range: -5.2534
Max Act: 5.0971. Min Act: -0.1700
Data Index: 2110933 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2534. Min Range: -5.2534
Max Act: 5.0971. Min Act: -0.1700
Data Index: 4220619 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2534. Min Range: -5.2534
Max Act: 4.9721. Min Act: -0.1700
Data Index: 2744826 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2534. Min Range: -5.2534
Max Act: 5.0034. Min Act: -0.1700
Data Index: 1195921 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2534. Min Range: -5.2534
Max Act: 4.9721. Min Act: -0.1700
Data Index: 8552976 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2534. Min Range: -5.2534
Max Act: 4.9409. Min Act: -0.1700
Data Index: 5260767 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2534. Min Range: -5.2534
Max Act: 4.9409. Min Act: -0.1700
Data Index: 8606983 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2534. Min Range: -5.2534
Max Act: 4.9409. Min Act: -0.1700
Data Index: 2899930 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2534. Min Range: -5.2534
Max Act: 4.9409. Min Act: -0.1700
Data Index: 7162331 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2534. Min Range: -5.2534
Max Act: 4.9409. Min Act: -0.1700
Data Index: 3923799 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2534. Min Range: -5.2534
Max Act: 4.9409. Min Act: -0.1700
Data Index: 5470015 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2534. Min Range: -5.2534
Max Act: 4.9096. Min Act: -0.1700
Data Index: 2491057 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2534. Min Range: -5.2534
Max Act: 4.9096. Min Act: -0.1700
Data Index: 4031183 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2534. Min Range: -5.2534
Max Act: 4.9096. Min Act: -0.1700
Data Index: 184670 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2534. Min Range: -5.2534
Max Act: 4.9409. Min Act: -0.1700
Data Index: 283025 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2534. Min Range: -5.2534
Max Act: 4.8784. Min Act: -0.1700
Data Index: 6018651 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19