Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5116 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0835. Min Range: -5.0835
Max Act: 5.0835. Min Act: -0.1700
Data Index: 4283705 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0835. Min Range: -5.0835
Max Act: 4.9585. Min Act: -0.1700
Data Index: 4411066 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0835. Min Range: -5.0835
Max Act: 4.7710. Min Act: -0.1700
Data Index: 1709773 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0835. Min Range: -5.0835
Max Act: 4.8023. Min Act: -0.1700
Data Index: 8290167 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0835. Min Range: -5.0835
Max Act: 4.7710. Min Act: -0.1700
Data Index: 3458240 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0835. Min Range: -5.0835
Max Act: 4.7710. Min Act: -0.1700
Data Index: 2466822 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0835. Min Range: -5.0835
Max Act: 4.7710. Min Act: -0.1700
Data Index: 2363605 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0835. Min Range: -5.0835
Max Act: 4.7710. Min Act: -0.1700
Data Index: 5576018 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0835. Min Range: -5.0835
Max Act: 4.7398. Min Act: -0.1700
Data Index: 7971656 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0835. Min Range: -5.0835
Max Act: 4.7398. Min Act: -0.1700
Data Index: 4283708 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0835. Min Range: -5.0835
Max Act: 4.7085. Min Act: -0.1700
Data Index: 678033 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0835. Min Range: -5.0835
Max Act: 4.7085. Min Act: -0.1700
Data Index: 4653603 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0835. Min Range: -5.0835
Max Act: 4.7085. Min Act: -0.1700
Data Index: 570539 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0835. Min Range: -5.0835
Max Act: 4.6773. Min Act: -0.1700
Data Index: 5368702 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0835. Min Range: -5.0835
Max Act: 4.6773. Min Act: -0.1700
Data Index: 5319970 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0835. Min Range: -5.0835
Max Act: 4.6773. Min Act: -0.1700
Data Index: 7794055 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0835. Min Range: -5.0835
Max Act: 4.6773. Min Act: -0.1700
Data Index: 8395663 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0835. Min Range: -5.0835
Max Act: 4.6773. Min Act: -0.1700
Data Index: 7662226 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0835. Min Range: -5.0835
Max Act: 4.6773. Min Act: -0.1700
Data Index: 2466821 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0835. Min Range: -5.0835
Max Act: 4.6773. Min Act: -0.1700
Data Index: 7476757 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #19