Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1899 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7367. Min Range: -2.7367
Max Act: 2.7367. Min Act: -0.1700
Data Index: 2773055 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7367. Min Range: -2.7367
Max Act: 2.5601. Min Act: -0.1700
Data Index: 1148385 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7367. Min Range: -2.7367
Max Act: 2.5278. Min Act: -0.1700
Data Index: 8008698 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7367. Min Range: -2.7367
Max Act: 2.4955. Min Act: -0.1700
Data Index: 7083828 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7367. Min Range: -2.7367
Max Act: 2.4305. Min Act: -0.1700
Data Index: 4504337 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7367. Min Range: -2.7367
Max Act: 2.4468. Min Act: -0.1700
Data Index: 6270328 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7367. Min Range: -2.7367
Max Act: 2.4793. Min Act: -0.1700
Data Index: 556589 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7367. Min Range: -2.7367
Max Act: 2.3816. Min Act: -0.1700
Data Index: 7336267 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7367. Min Range: -2.7367
Max Act: 2.4305. Min Act: -0.1700
Data Index: 1209497 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7367. Min Range: -2.7367
Max Act: 2.4305. Min Act: -0.1700
Data Index: 5047961 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7367. Min Range: -2.7367
Max Act: 2.4142. Min Act: -0.1700
Data Index: 7993922 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7367. Min Range: -2.7367
Max Act: 2.4142. Min Act: -0.1700
Data Index: 5033758 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7367. Min Range: -2.7367
Max Act: 2.4305. Min Act: -0.1700
Data Index: 8236115 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7367. Min Range: -2.7367
Max Act: 2.4305. Min Act: -0.1700
Data Index: 1832832 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7367. Min Range: -2.7367
Max Act: 2.4468. Min Act: -0.1700
Data Index: 2600518 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7367. Min Range: -2.7367
Max Act: 2.4305. Min Act: -0.1700
Data Index: 157426 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7367. Min Range: -2.7367
Max Act: 2.3816. Min Act: -0.1700
Data Index: 1073479 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7367. Min Range: -2.7367
Max Act: 2.4142. Min Act: -0.1700
Data Index: 3243407 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7367. Min Range: -2.7367
Max Act: 2.3816. Min Act: -0.1700
Data Index: 4528755 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7367. Min Range: -2.7367
Max Act: 2.3652. Min Act: -0.1700
Data Index: 1145524 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19