Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2647 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2020. Min Range: -4.2020
Max Act: 4.2020. Min Act: -0.1700
Data Index: 4151359 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2020. Min Range: -4.2020
Max Act: 4.2020. Min Act: -0.1700
Data Index: 3776100 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2020. Min Range: -4.2020
Max Act: 4.1395. Min Act: -0.1700
Data Index: 8667399 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2020. Min Range: -4.2020
Max Act: 4.0770. Min Act: -0.1700
Data Index: 8099564 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2020. Min Range: -4.2020
Max Act: 4.0770. Min Act: -0.1700
Data Index: 1975378 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2020. Min Range: -4.2020
Max Act: 4.0770. Min Act: -0.1700
Data Index: 3008171 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2020. Min Range: -4.2020
Max Act: 4.1082. Min Act: -0.1700
Data Index: 128585 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2020. Min Range: -4.2020
Max Act: 4.0770. Min Act: -0.1700
Data Index: 6809898 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2020. Min Range: -4.2020
Max Act: 4.0457. Min Act: -0.1700
Data Index: 2626203 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2020. Min Range: -4.2020
Max Act: 3.9832. Min Act: -0.1700
Data Index: 1779799 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2020. Min Range: -4.2020
Max Act: 3.9832. Min Act: -0.1700
Data Index: 1666284 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2020. Min Range: -4.2020
Max Act: 3.9832. Min Act: -0.1700
Data Index: 5273855 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2020. Min Range: -4.2020
Max Act: 3.9832. Min Act: -0.1700
Data Index: 2354616 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2020. Min Range: -4.2020
Max Act: 3.9519. Min Act: -0.1700
Data Index: 5282745 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2020. Min Range: -4.2020
Max Act: 3.9519. Min Act: -0.1700
Data Index: 5967672 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2020. Min Range: -4.2020
Max Act: 3.8894. Min Act: -0.1700
Data Index: 5155653 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2020. Min Range: -4.2020
Max Act: 3.9207. Min Act: -0.1700
Data Index: 6148141 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2020. Min Range: -4.2020
Max Act: 3.9207. Min Act: -0.1700
Data Index: 58697 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2020. Min Range: -4.2020
Max Act: 3.9207. Min Act: -0.1700
Data Index: 4943325 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2020. Min Range: -4.2020
Max Act: 3.8894. Min Act: -0.1700
Data Index: 6310195 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #19