Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1989 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0352. Min Range: -5.0352
Max Act: 5.0352. Min Act: -0.1700
Data Index: 5127858 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0352. Min Range: -5.0352
Max Act: 4.8165. Min Act: -0.1700
Data Index: 2679664 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0352. Min Range: -5.0352
Max Act: 4.8165. Min Act: -0.1700
Data Index: 8798204 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0352. Min Range: -5.0352
Max Act: 4.7852. Min Act: -0.1700
Data Index: 6575131 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0352. Min Range: -5.0352
Max Act: 4.7852. Min Act: -0.1700
Data Index: 6083300 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0352. Min Range: -5.0352
Max Act: 4.7540. Min Act: -0.1700
Data Index: 3160736 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0352. Min Range: -5.0352
Max Act: 4.7227. Min Act: -0.1700
Data Index: 3121910 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0352. Min Range: -5.0352
Max Act: 4.7227. Min Act: -0.1700
Data Index: 8296729 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0352. Min Range: -5.0352
Max Act: 4.6915. Min Act: -0.1700
Data Index: 1624790 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0352. Min Range: -5.0352
Max Act: 4.6602. Min Act: -0.1700
Data Index: 4280883 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0352. Min Range: -5.0352
Max Act: 4.6290. Min Act: -0.1700
Data Index: 3583936 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0352. Min Range: -5.0352
Max Act: 4.6290. Min Act: -0.1700
Data Index: 2934441 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0352. Min Range: -5.0352
Max Act: 4.6290. Min Act: -0.1700
Data Index: 59000 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0352. Min Range: -5.0352
Max Act: 4.5977. Min Act: -0.1700
Data Index: 7262334 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0352. Min Range: -5.0352
Max Act: 4.6290. Min Act: -0.1700
Data Index: 6759860 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0352. Min Range: -5.0352
Max Act: 4.5977. Min Act: -0.1700
Data Index: 3583934 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0352. Min Range: -5.0352
Max Act: 4.5977. Min Act: -0.1700
Data Index: 2873911 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0352. Min Range: -5.0352
Max Act: 4.5665. Min Act: -0.1700
Data Index: 6245668 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0352. Min Range: -5.0352
Max Act: 4.5352. Min Act: -0.1700
Data Index: 1536741 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0352. Min Range: -5.0352
Max Act: 4.5352. Min Act: -0.1700
Data Index: 5027182 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19