Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 283 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8269. Min Range: -5.8269
Max Act: 5.8269. Min Act: -0.1700
Data Index: 5069944 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8269. Min Range: -5.8269
Max Act: 5.8269. Min Act: -0.1700
Data Index: 2567535 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8269. Min Range: -5.8269
Max Act: 5.7331. Min Act: -0.1700
Data Index: 3659546 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8269. Min Range: -5.8269
Max Act: 5.7644. Min Act: -0.1700
Data Index: 6033249 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8269. Min Range: -5.8269
Max Act: 5.7644. Min Act: -0.1700
Data Index: 5530371 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8269. Min Range: -5.8269
Max Act: 5.7331. Min Act: -0.1700
Data Index: 8404828 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8269. Min Range: -5.8269
Max Act: 5.7331. Min Act: -0.1700
Data Index: 6570766 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8269. Min Range: -5.8269
Max Act: 5.7331. Min Act: -0.1700
Data Index: 6751533 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8269. Min Range: -5.8269
Max Act: 5.7019. Min Act: -0.1700
Data Index: 5772358 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8269. Min Range: -5.8269
Max Act: 5.7331. Min Act: -0.1700
Data Index: 3997989 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8269. Min Range: -5.8269
Max Act: 5.7019. Min Act: -0.1700
Data Index: 3962683 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8269. Min Range: -5.8269
Max Act: 5.7644. Min Act: -0.1700
Data Index: 2702981 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8269. Min Range: -5.8269
Max Act: 5.6706. Min Act: -0.1700
Data Index: 3887656 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8269. Min Range: -5.8269
Max Act: 5.7331. Min Act: -0.1700
Data Index: 2007437 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8269. Min Range: -5.8269
Max Act: 5.7019. Min Act: -0.1700
Data Index: 7754696 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8269. Min Range: -5.8269
Max Act: 5.7019. Min Act: -0.1700
Data Index: 8776959 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8269. Min Range: -5.8269
Max Act: 5.6706. Min Act: -0.1700
Data Index: 2691168 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8269. Min Range: -5.8269
Max Act: 5.7019. Min Act: -0.1700
Data Index: 851404 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8269. Min Range: -5.8269
Max Act: 5.7019. Min Act: -0.1700
Data Index: 7399611 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8269. Min Range: -5.8269
Max Act: 5.6706. Min Act: -0.1700
Data Index: 4271244 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19