Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5551 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6493. Min Range: -6.6493
Max Act: 6.6493. Min Act: -0.1700
Data Index: 3659845 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6493. Min Range: -6.6493
Max Act: 6.6493. Min Act: -0.1700
Data Index: 1510717 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6493. Min Range: -6.6493
Max Act: 6.3993. Min Act: -0.1700
Data Index: 6111588 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6493. Min Range: -6.6493
Max Act: 6.3056. Min Act: -0.1700
Data Index: 3538633 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6493. Min Range: -6.6493
Max Act: 6.3056. Min Act: -0.1700
Data Index: 4503151 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6493. Min Range: -6.6493
Max Act: 6.2118. Min Act: -0.1700
Data Index: 6681143 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6493. Min Range: -6.6493
Max Act: 6.1806. Min Act: -0.1700
Data Index: 5017830 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6493. Min Range: -6.6493
Max Act: 6.1806. Min Act: -0.1700
Data Index: 5175796 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6493. Min Range: -6.6493
Max Act: 6.0868. Min Act: -0.1700
Data Index: 5658865 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6493. Min Range: -6.6493
Max Act: 6.1181. Min Act: -0.1700
Data Index: 7906057 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6493. Min Range: -6.6493
Max Act: 6.0868. Min Act: -0.1700
Data Index: 5336763 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6493. Min Range: -6.6493
Max Act: 6.0868. Min Act: -0.1700
Data Index: 7234602 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6493. Min Range: -6.6493
Max Act: 6.0556. Min Act: -0.1700
Data Index: 861310 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6493. Min Range: -6.6493
Max Act: 6.0556. Min Act: -0.1700
Data Index: 1417904 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6493. Min Range: -6.6493
Max Act: 6.0243. Min Act: -0.1700
Data Index: 125618 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6493. Min Range: -6.6493
Max Act: 6.0243. Min Act: -0.1700
Data Index: 6856408 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6493. Min Range: -6.6493
Max Act: 6.0243. Min Act: -0.1700
Data Index: 4799098 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6493. Min Range: -6.6493
Max Act: 6.0243. Min Act: -0.1700
Data Index: 5709701 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6493. Min Range: -6.6493
Max Act: 5.9931. Min Act: -0.1700
Data Index: 4934805 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6493. Min Range: -6.6493
Max Act: 5.9931. Min Act: -0.1700
Data Index: 5290197 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #19