Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4559 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5714. Min Range: -6.5714
Max Act: 6.5714. Min Act: -0.1700
Data Index: 6195558 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5714. Min Range: -6.5714
Max Act: 6.4151. Min Act: -0.1700
Data Index: 5821820 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5714. Min Range: -6.5714
Max Act: 6.3526. Min Act: -0.1700
Data Index: 5302447 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5714. Min Range: -6.5714
Max Act: 6.3526. Min Act: -0.1700
Data Index: 6831653 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5714. Min Range: -6.5714
Max Act: 6.3526. Min Act: -0.1700
Data Index: 8770568 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5714. Min Range: -6.5714
Max Act: 6.3214. Min Act: -0.1700
Data Index: 8608564 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5714. Min Range: -6.5714
Max Act: 6.3214. Min Act: -0.1700
Data Index: 5167234 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5714. Min Range: -6.5714
Max Act: 6.3214. Min Act: -0.1700
Data Index: 3804340 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5714. Min Range: -6.5714
Max Act: 6.2589. Min Act: -0.1700
Data Index: 2341230 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5714. Min Range: -6.5714
Max Act: 6.2901. Min Act: -0.1700
Data Index: 7475661 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5714. Min Range: -6.5714
Max Act: 6.2901. Min Act: -0.1700
Data Index: 5061172 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5714. Min Range: -6.5714
Max Act: 6.2901. Min Act: -0.1700
Data Index: 2071918 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5714. Min Range: -6.5714
Max Act: 6.2901. Min Act: -0.1700
Data Index: 2181646 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5714. Min Range: -6.5714
Max Act: 6.2589. Min Act: -0.1700
Data Index: 4162804 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5714. Min Range: -6.5714
Max Act: 6.2901. Min Act: -0.1700
Data Index: 4307728 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5714. Min Range: -6.5714
Max Act: 6.2589. Min Act: -0.1700
Data Index: 8191290 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5714. Min Range: -6.5714
Max Act: 6.2589. Min Act: -0.1700
Data Index: 1576626 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5714. Min Range: -6.5714
Max Act: 6.2276. Min Act: -0.1700
Data Index: 6718102 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5714. Min Range: -6.5714
Max Act: 6.2276. Min Act: -0.1700
Data Index: 8824433 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5714. Min Range: -6.5714
Max Act: 6.1964. Min Act: -0.1700
Data Index: 6995105 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #19