Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 752 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9335. Min Range: -4.9335
Max Act: 4.9335. Min Act: -0.1700
Data Index: 2505679 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9335. Min Range: -4.9335
Max Act: 4.7772. Min Act: -0.1700
Data Index: 4167473 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9335. Min Range: -4.9335
Max Act: 4.8085. Min Act: -0.1700
Data Index: 8212832 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9335. Min Range: -4.9335
Max Act: 4.7147. Min Act: -0.1700
Data Index: 541852 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9335. Min Range: -4.9335
Max Act: 4.7460. Min Act: -0.1700
Data Index: 4927617 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9335. Min Range: -4.9335
Max Act: 4.7772. Min Act: -0.1700
Data Index: 7865853 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9335. Min Range: -4.9335
Max Act: 4.6210. Min Act: -0.1700
Data Index: 1134283 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9335. Min Range: -4.9335
Max Act: 4.6522. Min Act: -0.1700
Data Index: 7731686 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9335. Min Range: -4.9335
Max Act: 4.6210. Min Act: -0.1700
Data Index: 4459466 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9335. Min Range: -4.9335
Max Act: 4.6210. Min Act: -0.1700
Data Index: 2794468 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9335. Min Range: -4.9335
Max Act: 4.6210. Min Act: -0.1700
Data Index: 447978 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9335. Min Range: -4.9335
Max Act: 4.6210. Min Act: -0.1700
Data Index: 310142 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9335. Min Range: -4.9335
Max Act: 4.6210. Min Act: -0.1700
Data Index: 7173408 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9335. Min Range: -4.9335
Max Act: 4.5897. Min Act: -0.1700
Data Index: 148272 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9335. Min Range: -4.9335
Max Act: 4.5897. Min Act: -0.1700
Data Index: 3810418 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9335. Min Range: -4.9335
Max Act: 4.5585. Min Act: -0.1700
Data Index: 4749619 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9335. Min Range: -4.9335
Max Act: 4.5897. Min Act: -0.1700
Data Index: 2043323 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9335. Min Range: -4.9335
Max Act: 4.5585. Min Act: -0.1700
Data Index: 4052823 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9335. Min Range: -4.9335
Max Act: 4.5585. Min Act: -0.1700
Data Index: 4083481 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9335. Min Range: -4.9335
Max Act: 4.5585. Min Act: -0.1700
Data Index: 434198 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19