Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3625 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.1902. Min Range: -2.1902
Max Act: 2.1902. Min Act: -0.1700
Data Index: 3854572 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1902. Min Range: -2.1902
Max Act: 2.1569. Min Act: -0.1700
Data Index: 8450513 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1902. Min Range: -2.1902
Max Act: 2.1569. Min Act: -0.1700
Data Index: 7348646 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1902. Min Range: -2.1902
Max Act: 2.1403. Min Act: -0.1700
Data Index: 2810108 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1902. Min Range: -2.1902
Max Act: 2.1403. Min Act: -0.1700
Data Index: 3057899 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1902. Min Range: -2.1902
Max Act: 2.1236. Min Act: -0.1700
Data Index: 4905838 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1902. Min Range: -2.1902
Max Act: 2.1236. Min Act: -0.1700
Data Index: 7622943 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1902. Min Range: -2.1902
Max Act: 2.1236. Min Act: -0.1700
Data Index: 3057896 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1902. Min Range: -2.1902
Max Act: 2.1403. Min Act: -0.1699
Data Index: 2390660 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1902. Min Range: -2.1902
Max Act: 2.1068. Min Act: -0.1700
Data Index: 4096607 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1902. Min Range: -2.1902
Max Act: 2.1068. Min Act: -0.1700
Data Index: 4416144 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1902. Min Range: -2.1902
Max Act: 2.1068. Min Act: -0.1700
Data Index: 7232896 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1902. Min Range: -2.1902
Max Act: 2.0901. Min Act: -0.1700
Data Index: 337129 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1902. Min Range: -2.1902
Max Act: 2.1068. Min Act: -0.1700
Data Index: 6037546 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1902. Min Range: -2.1902
Max Act: 2.1068. Min Act: -0.1700
Data Index: 8450512 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1902. Min Range: -2.1902
Max Act: 2.0733. Min Act: -0.1700
Data Index: 1837547 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1902. Min Range: -2.1902
Max Act: 2.0901. Min Act: -0.1700
Data Index: 4342352 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1902. Min Range: -2.1902
Max Act: 2.0901. Min Act: -0.1700
Data Index: 1730615 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1902. Min Range: -2.1902
Max Act: 2.0733. Min Act: -0.1700
Data Index: 2117081 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1902. Min Range: -2.1902
Max Act: 2.0733. Min Act: -0.1700
Data Index: 2668598 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #19