Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2343 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.1655. Min Range: -8.1655
Max Act: 8.1655. Min Act: -0.1700
Data Index: 5883320 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1655. Min Range: -8.1655
Max Act: 7.9780. Min Act: -0.1700
Data Index: 2616460 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1655. Min Range: -8.1655
Max Act: 7.9780. Min Act: -0.1700
Data Index: 5581628 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1655. Min Range: -8.1655
Max Act: 7.9467. Min Act: -0.1700
Data Index: 689038 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1655. Min Range: -8.1655
Max Act: 7.9780. Min Act: -0.1700
Data Index: 2308233 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1655. Min Range: -8.1655
Max Act: 7.8530. Min Act: -0.1700
Data Index: 3308028 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1655. Min Range: -8.1655
Max Act: 7.9155. Min Act: -0.1700
Data Index: 6702702 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1655. Min Range: -8.1655
Max Act: 7.9155. Min Act: -0.1700
Data Index: 3781484 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1655. Min Range: -8.1655
Max Act: 7.8842. Min Act: -0.1700
Data Index: 34280 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1655. Min Range: -8.1655
Max Act: 7.8842. Min Act: -0.1700
Data Index: 7341624 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1655. Min Range: -8.1655
Max Act: 7.8530. Min Act: -0.1700
Data Index: 7957661 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1655. Min Range: -8.1655
Max Act: 7.8530. Min Act: -0.1700
Data Index: 8518030 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1655. Min Range: -8.1655
Max Act: 7.9155. Min Act: -0.1700
Data Index: 4306842 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1655. Min Range: -8.1655
Max Act: 7.8217. Min Act: -0.1700
Data Index: 2058940 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1655. Min Range: -8.1655
Max Act: 7.8842. Min Act: -0.1700
Data Index: 1304060 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1655. Min Range: -8.1655
Max Act: 7.7905. Min Act: -0.1700
Data Index: 8018965 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1655. Min Range: -8.1655
Max Act: 7.7905. Min Act: -0.1700
Data Index: 7902758 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1655. Min Range: -8.1655
Max Act: 7.8217. Min Act: -0.1700
Data Index: 5050763 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1655. Min Range: -8.1655
Max Act: 7.7592. Min Act: -0.1700
Data Index: 26718 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1655. Min Range: -8.1655
Max Act: 7.7280. Min Act: -0.1700
Data Index: 350767 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #19