Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3070 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1452. Min Range: -6.1452
Max Act: 6.1452. Min Act: -0.1700
Data Index: 5208569 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1452. Min Range: -6.1452
Max Act: 6.0202. Min Act: -0.1700
Data Index: 3885849 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1452. Min Range: -6.1452
Max Act: 5.9264. Min Act: -0.1700
Data Index: 3377411 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1452. Min Range: -6.1452
Max Act: 5.8014. Min Act: -0.1700
Data Index: 476265 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1452. Min Range: -6.1452
Max Act: 5.7389. Min Act: -0.1700
Data Index: 5284508 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1452. Min Range: -6.1452
Max Act: 5.7389. Min Act: -0.1700
Data Index: 6262025 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1452. Min Range: -6.1452
Max Act: 5.6764. Min Act: -0.1700
Data Index: 3363112 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1452. Min Range: -6.1452
Max Act: 5.6764. Min Act: -0.1700
Data Index: 6347768 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1452. Min Range: -6.1452
Max Act: 5.6452. Min Act: -0.1700
Data Index: 165313 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1452. Min Range: -6.1452
Max Act: 5.6452. Min Act: -0.1700
Data Index: 7881738 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1452. Min Range: -6.1452
Max Act: 5.6452. Min Act: -0.1700
Data Index: 932792 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1452. Min Range: -6.1452
Max Act: 5.5514. Min Act: -0.1700
Data Index: 8522968 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1452. Min Range: -6.1452
Max Act: 5.5514. Min Act: -0.1700
Data Index: 3659577 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1452. Min Range: -6.1452
Max Act: 5.5202. Min Act: -0.1700
Data Index: 1778129 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1452. Min Range: -6.1452
Max Act: 5.5514. Min Act: -0.1700
Data Index: 7065350 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1452. Min Range: -6.1452
Max Act: 5.5514. Min Act: -0.1700
Data Index: 4843566 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1452. Min Range: -6.1452
Max Act: 5.5202. Min Act: -0.1700
Data Index: 7221014 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1452. Min Range: -6.1452
Max Act: 5.5514. Min Act: -0.1700
Data Index: 8169657 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1452. Min Range: -6.1452
Max Act: 5.5514. Min Act: -0.1700
Data Index: 6080682 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1452. Min Range: -6.1452
Max Act: 5.5514. Min Act: -0.1700
Data Index: 3907251 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #19