Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3089 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.4351. Min Range: -8.4351
Max Act: 8.4351. Min Act: -0.1700
Data Index: 8090549 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4351. Min Range: -8.4351
Max Act: 8.3726. Min Act: -0.1700
Data Index: 3748452 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4351. Min Range: -8.4351
Max Act: 8.3101. Min Act: -0.1700
Data Index: 8097220 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4351. Min Range: -8.4351
Max Act: 8.2476. Min Act: -0.1700
Data Index: 8477136 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4351. Min Range: -8.4351
Max Act: 8.2476. Min Act: -0.1700
Data Index: 1021840 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4351. Min Range: -8.4351
Max Act: 8.0601. Min Act: -0.1700
Data Index: 39958 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4351. Min Range: -8.4351
Max Act: 8.0601. Min Act: -0.1700
Data Index: 4685150 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4351. Min Range: -8.4351
Max Act: 7.9976. Min Act: -0.1700
Data Index: 6799749 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4351. Min Range: -8.4351
Max Act: 7.9351. Min Act: -0.1700
Data Index: 2684616 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4351. Min Range: -8.4351
Max Act: 7.8726. Min Act: -0.1700
Data Index: 2367296 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4351. Min Range: -8.4351
Max Act: 7.8101. Min Act: -0.1700
Data Index: 4081367 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4351. Min Range: -8.4351
Max Act: 7.8726. Min Act: -0.1700
Data Index: 6035737 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4351. Min Range: -8.4351
Max Act: 7.8101. Min Act: -0.1700
Data Index: 8347264 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4351. Min Range: -8.4351
Max Act: 7.8101. Min Act: -0.1700
Data Index: 7087884 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4351. Min Range: -8.4351
Max Act: 7.8101. Min Act: -0.1700
Data Index: 2888954 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4351. Min Range: -8.4351
Max Act: 7.8101. Min Act: -0.1700
Data Index: 8590836 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4351. Min Range: -8.4351
Max Act: 7.8101. Min Act: -0.1700
Data Index: 410452 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4351. Min Range: -8.4351
Max Act: 7.8101. Min Act: -0.1700
Data Index: 5097703 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4351. Min Range: -8.4351
Max Act: 7.7476. Min Act: -0.1700
Data Index: 7702954 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4351. Min Range: -8.4351
Max Act: 7.7476. Min Act: -0.1700
Data Index: 4770613 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #19