Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2716 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8008. Min Range: -6.8008
Max Act: 6.8008. Min Act: -0.1699
Data Index: 8638399 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8008. Min Range: -6.8008
Max Act: 6.7071. Min Act: -0.1698
Data Index: 2151666 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8008. Min Range: -6.8008
Max Act: 6.6133. Min Act: -0.1700
Data Index: 1880552 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8008. Min Range: -6.8008
Max Act: 6.5508. Min Act: -0.1700
Data Index: 6328484 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8008. Min Range: -6.8008
Max Act: 6.4883. Min Act: -0.1681
Data Index: 8797000 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8008. Min Range: -6.8008
Max Act: 6.4258. Min Act: -0.1700
Data Index: 4039732 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8008. Min Range: -6.8008
Max Act: 6.4258. Min Act: -0.1700
Data Index: 3799586 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8008. Min Range: -6.8008
Max Act: 6.3946. Min Act: -0.1700
Data Index: 4391950 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8008. Min Range: -6.8008
Max Act: 6.3633. Min Act: -0.1698
Data Index: 943864 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8008. Min Range: -6.8008
Max Act: 6.3008. Min Act: -0.1700
Data Index: 8255632 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8008. Min Range: -6.8008
Max Act: 6.3008. Min Act: -0.1595
Data Index: 2581312 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8008. Min Range: -6.8008
Max Act: 6.3008. Min Act: -0.1700
Data Index: 5085026 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8008. Min Range: -6.8008
Max Act: 6.2696. Min Act: -0.1700
Data Index: 8268928 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8008. Min Range: -6.8008
Max Act: 6.1758. Min Act: -0.1700
Data Index: 2524377 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8008. Min Range: -6.8008
Max Act: 6.1758. Min Act: -0.1700
Data Index: 8638405 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8008. Min Range: -6.8008
Max Act: 6.1446. Min Act: -0.1700
Data Index: 2951943 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8008. Min Range: -6.8008
Max Act: 6.1446. Min Act: -0.1700
Data Index: 701704 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8008. Min Range: -6.8008
Max Act: 6.2071. Min Act: -0.1700
Data Index: 3545388 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8008. Min Range: -6.8008
Max Act: 6.1446. Min Act: -0.1699
Data Index: 4645510 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8008. Min Range: -6.8008
Max Act: 6.1133. Min Act: -0.1684
Data Index: 32888 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19