Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2966 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6339. Min Range: -6.6339
Max Act: 6.6339. Min Act: -0.1700
Data Index: 4103282 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6339. Min Range: -6.6339
Max Act: 6.1652. Min Act: -0.1700
Data Index: 2916380 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6339. Min Range: -6.6339
Max Act: 6.0089. Min Act: -0.1700
Data Index: 1166933 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6339. Min Range: -6.6339
Max Act: 5.8839. Min Act: -0.1700
Data Index: 8159348 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6339. Min Range: -6.6339
Max Act: 5.8839. Min Act: -0.1700
Data Index: 4149262 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6339. Min Range: -6.6339
Max Act: 5.8527. Min Act: -0.1700
Data Index: 5551441 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6339. Min Range: -6.6339
Max Act: 5.8839. Min Act: -0.1700
Data Index: 8399384 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6339. Min Range: -6.6339
Max Act: 5.8839. Min Act: -0.1700
Data Index: 5657788 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6339. Min Range: -6.6339
Max Act: 5.8214. Min Act: -0.1700
Data Index: 766655 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6339. Min Range: -6.6339
Max Act: 5.8214. Min Act: -0.1700
Data Index: 1911536 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6339. Min Range: -6.6339
Max Act: 5.8527. Min Act: -0.1700
Data Index: 3546299 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6339. Min Range: -6.6339
Max Act: 5.7589. Min Act: -0.1700
Data Index: 6199005 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6339. Min Range: -6.6339
Max Act: 5.7589. Min Act: -0.1700
Data Index: 4232948 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6339. Min Range: -6.6339
Max Act: 5.7277. Min Act: -0.1700
Data Index: 4707795 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6339. Min Range: -6.6339
Max Act: 5.7277. Min Act: -0.1700
Data Index: 1678022 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6339. Min Range: -6.6339
Max Act: 5.7277. Min Act: -0.1700
Data Index: 4356780 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6339. Min Range: -6.6339
Max Act: 5.7589. Min Act: -0.1700
Data Index: 7032323 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6339. Min Range: -6.6339
Max Act: 5.7277. Min Act: -0.1700
Data Index: 8120388 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6339. Min Range: -6.6339
Max Act: 5.6652. Min Act: -0.1700
Data Index: 1504495 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6339. Min Range: -6.6339
Max Act: 5.6652. Min Act: -0.1700
Data Index: 512046 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #19