Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2451 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.5014. Min Act: -0.1700
Data Index: 2498329 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.4077. Min Act: -0.1700
Data Index: 3867429 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.3764. Min Act: -0.1700
Data Index: 892577 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.3139. Min Act: -0.1700
Data Index: 6827275 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.2827. Min Act: -0.1700
Data Index: 7337509 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.2827. Min Act: -0.1700
Data Index: 8158399 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.2202. Min Act: -0.1700
Data Index: 3900534 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.2514. Min Act: -0.1700
Data Index: 7295979 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.2514. Min Act: -0.1700
Data Index: 3333677 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.2514. Min Act: -0.1700
Data Index: 8800175 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.1889. Min Act: -0.1700
Data Index: 6443738 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.1577. Min Act: -0.1700
Data Index: 3460366 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.1577. Min Act: -0.1700
Data Index: 8106072 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.1577. Min Act: -0.1700
Data Index: 570736 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.1264. Min Act: -0.1700
Data Index: 2986243 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.1264. Min Act: -0.1700
Data Index: 7540250 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.0952. Min Act: -0.1700
Data Index: 2907620 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.0952. Min Act: -0.1700
Data Index: 3924980 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.0952. Min Act: -0.1700
Data Index: 4748230 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.0952. Min Act: -0.1700
Data Index: 5512296 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #19