Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3863 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.0425. Min Range: -8.0425
Max Act: 8.0425. Min Act: -0.1700
Data Index: 5378180 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0425. Min Range: -8.0425
Max Act: 7.9800. Min Act: -0.1700
Data Index: 1695050 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0425. Min Range: -8.0425
Max Act: 7.9175. Min Act: -0.1700
Data Index: 2253001 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0425. Min Range: -8.0425
Max Act: 7.9175. Min Act: -0.1700
Data Index: 4251826 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0425. Min Range: -8.0425
Max Act: 7.8862. Min Act: -0.1700
Data Index: 7357756 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0425. Min Range: -8.0425
Max Act: 7.8237. Min Act: -0.1700
Data Index: 7416175 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0425. Min Range: -8.0425
Max Act: 7.8237. Min Act: -0.1700
Data Index: 6016757 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0425. Min Range: -8.0425
Max Act: 7.8237. Min Act: -0.1700
Data Index: 8646500 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0425. Min Range: -8.0425
Max Act: 7.7300. Min Act: -0.1700
Data Index: 4987344 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0425. Min Range: -8.0425
Max Act: 7.6987. Min Act: -0.1700
Data Index: 2115121 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0425. Min Range: -8.0425
Max Act: 7.6675. Min Act: -0.1700
Data Index: 954373 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0425. Min Range: -8.0425
Max Act: 7.6675. Min Act: -0.1700
Data Index: 3583982 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0425. Min Range: -8.0425
Max Act: 7.6675. Min Act: -0.1700
Data Index: 2085112 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0425. Min Range: -8.0425
Max Act: 7.6362. Min Act: -0.1700
Data Index: 1444105 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0425. Min Range: -8.0425
Max Act: 7.6362. Min Act: -0.1700
Data Index: 5559419 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0425. Min Range: -8.0425
Max Act: 7.6362. Min Act: -0.1700
Data Index: 7939280 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0425. Min Range: -8.0425
Max Act: 7.6362. Min Act: -0.1700
Data Index: 2377582 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0425. Min Range: -8.0425
Max Act: 7.5737. Min Act: -0.1700
Data Index: 4900878 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0425. Min Range: -8.0425
Max Act: 7.5737. Min Act: -0.1700
Data Index: 3879368 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0425. Min Range: -8.0425
Max Act: 7.5737. Min Act: -0.1700
Data Index: 3723860 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #19