Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1200 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3847. Min Range: -5.3847
Max Act: 5.3847. Min Act: -0.1700
Data Index: 6784816 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3847. Min Range: -5.3847
Max Act: 5.3535. Min Act: -0.1700
Data Index: 1387593 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3847. Min Range: -5.3847
Max Act: 5.3535. Min Act: -0.1700
Data Index: 4784808 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3847. Min Range: -5.3847
Max Act: 5.2910. Min Act: -0.1700
Data Index: 597220 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3847. Min Range: -5.3847
Max Act: 5.2597. Min Act: -0.1700
Data Index: 697912 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3847. Min Range: -5.3847
Max Act: 5.2597. Min Act: -0.1700
Data Index: 2527283 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3847. Min Range: -5.3847
Max Act: 5.1972. Min Act: -0.1700
Data Index: 1028967 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3847. Min Range: -5.3847
Max Act: 5.1660. Min Act: -0.1700
Data Index: 6439668 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3847. Min Range: -5.3847
Max Act: 5.1347. Min Act: -0.1700
Data Index: 4234911 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3847. Min Range: -5.3847
Max Act: 5.0722. Min Act: -0.1700
Data Index: 1409450 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3847. Min Range: -5.3847
Max Act: 5.0722. Min Act: -0.1700
Data Index: 8017458 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3847. Min Range: -5.3847
Max Act: 5.0410. Min Act: -0.1700
Data Index: 2320702 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3847. Min Range: -5.3847
Max Act: 5.0410. Min Act: -0.1700
Data Index: 4489496 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3847. Min Range: -5.3847
Max Act: 5.0410. Min Act: -0.1700
Data Index: 964004 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3847. Min Range: -5.3847
Max Act: 5.0722. Min Act: -0.1700
Data Index: 651773 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3847. Min Range: -5.3847
Max Act: 5.0410. Min Act: -0.1700
Data Index: 7733133 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3847. Min Range: -5.3847
Max Act: 5.0097. Min Act: -0.1700
Data Index: 8253614 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3847. Min Range: -5.3847
Max Act: 4.9785. Min Act: -0.1700
Data Index: 1920453 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3847. Min Range: -5.3847
Max Act: 5.0097. Min Act: -0.1700
Data Index: 732599 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3847. Min Range: -5.3847
Max Act: 4.9785. Min Act: -0.1700
Data Index: 4449735 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #19