Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1690 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6594. Min Range: -6.6594
Max Act: 6.6594. Min Act: -0.1700
Data Index: 6990035 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6594. Min Range: -6.6594
Max Act: 6.6281. Min Act: -0.1700
Data Index: 155122 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6594. Min Range: -6.6594
Max Act: 6.5031. Min Act: -0.1700
Data Index: 3440839 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6594. Min Range: -6.6594
Max Act: 6.4719. Min Act: -0.1700
Data Index: 5584407 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6594. Min Range: -6.6594
Max Act: 6.4094. Min Act: -0.1700
Data Index: 7965072 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6594. Min Range: -6.6594
Max Act: 6.3781. Min Act: -0.1700
Data Index: 570366 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6594. Min Range: -6.6594
Max Act: 6.3781. Min Act: -0.1700
Data Index: 6069096 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6594. Min Range: -6.6594
Max Act: 6.3781. Min Act: -0.1700
Data Index: 3106201 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6594. Min Range: -6.6594
Max Act: 6.3156. Min Act: -0.1700
Data Index: 3782140 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6594. Min Range: -6.6594
Max Act: 6.3469. Min Act: -0.1700
Data Index: 7284799 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6594. Min Range: -6.6594
Max Act: 6.3469. Min Act: -0.1700
Data Index: 2775116 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6594. Min Range: -6.6594
Max Act: 6.3469. Min Act: -0.1700
Data Index: 1526620 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6594. Min Range: -6.6594
Max Act: 6.3156. Min Act: -0.1700
Data Index: 1171929 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6594. Min Range: -6.6594
Max Act: 6.3469. Min Act: -0.1700
Data Index: 741098 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6594. Min Range: -6.6594
Max Act: 6.3156. Min Act: -0.1700
Data Index: 4768330 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6594. Min Range: -6.6594
Max Act: 6.2844. Min Act: -0.1700
Data Index: 3559690 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6594. Min Range: -6.6594
Max Act: 6.3156. Min Act: -0.1700
Data Index: 5032731 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6594. Min Range: -6.6594
Max Act: 6.3156. Min Act: -0.1700
Data Index: 7078329 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6594. Min Range: -6.6594
Max Act: 6.3156. Min Act: -0.1700
Data Index: 7469969 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6594. Min Range: -6.6594
Max Act: 6.3156. Min Act: -0.1700
Data Index: 1578156 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19