Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3514 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.6777. Min Range: -0.6777
Max Act: 0.6777. Min Act: -0.1700
Data Index: 8180507 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6777. Min Range: -0.6777
Max Act: 0.6454. Min Act: -0.1696
Data Index: 7742350 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6777. Min Range: -0.6777
Max Act: 0.6215. Min Act: -0.1609
Data Index: 4085276 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6777. Min Range: -0.6777
Max Act: 0.5978. Min Act: -0.1693
Data Index: 4648767 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6777. Min Range: -0.6777
Max Act: 0.5743. Min Act: -0.1589
Data Index: 8180505 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6777. Min Range: -0.6777
Max Act: 0.5821. Min Act: -0.1692
Data Index: 2023714 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6777. Min Range: -0.6777
Max Act: 0.5821. Min Act: -0.1700
Data Index: 163347 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6777. Min Range: -0.6777
Max Act: 0.5281. Min Act: -0.1662
Data Index: 3915742 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6777. Min Range: -0.6777
Max Act: 0.5054. Min Act: -0.1674
Data Index: 140097 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6777. Min Range: -0.6777
Max Act: 0.4979. Min Act: -0.1698
Data Index: 2754356 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6777. Min Range: -0.6777
Max Act: 0.4979. Min Act: -0.1611
Data Index: 8484939 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6777. Min Range: -0.6777
Max Act: 0.4755. Min Act: -0.1700
Data Index: 1723332 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6777. Min Range: -0.6777
Max Act: 0.4830. Min Act: -0.1627
Data Index: 385108 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6777. Min Range: -0.6777
Max Act: 0.4904. Min Act: -0.1618
Data Index: 2547461 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6777. Min Range: -0.6777
Max Act: 0.4830. Min Act: -0.1696
Data Index: 8488893 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6777. Min Range: -0.6777
Max Act: 0.4830. Min Act: -0.1699
Data Index: 2055674 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6777. Min Range: -0.6777
Max Act: 0.4830. Min Act: -0.1700
Data Index: 385107 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6777. Min Range: -0.6777
Max Act: 0.4681. Min Act: -0.1700
Data Index: 3896543 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6777. Min Range: -0.6777
Max Act: 0.4681. Min Act: -0.1662
Data Index: 2404100 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6777. Min Range: -0.6777
Max Act: 0.4681. Min Act: -0.1700
Data Index: 7112150 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19