Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2711 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4678. Min Range: -3.4678
Max Act: 3.4678. Min Act: -0.1700
Data Index: 7736136 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4678. Min Range: -3.4678
Max Act: 3.3738. Min Act: -0.1700
Data Index: 3002313 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4678. Min Range: -3.4678
Max Act: 3.3581. Min Act: -0.1700
Data Index: 5155635 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4678. Min Range: -3.4678
Max Act: 3.3110. Min Act: -0.1700
Data Index: 7500393 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4678. Min Range: -3.4678
Max Act: 3.3110. Min Act: -0.1700
Data Index: 8429792 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4678. Min Range: -3.4678
Max Act: 3.2953. Min Act: -0.1700
Data Index: 1948575 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4678. Min Range: -3.4678
Max Act: 3.2796. Min Act: -0.1700
Data Index: 534624 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4678. Min Range: -3.4678
Max Act: 3.2639. Min Act: -0.1700
Data Index: 8546106 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4678. Min Range: -3.4678
Max Act: 3.2796. Min Act: -0.1700
Data Index: 8524814 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4678. Min Range: -3.4678
Max Act: 3.2639. Min Act: -0.1700
Data Index: 2788174 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4678. Min Range: -3.4678
Max Act: 3.2325. Min Act: -0.1700
Data Index: 8004260 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4678. Min Range: -3.4678
Max Act: 3.2325. Min Act: -0.1700
Data Index: 7980740 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4678. Min Range: -3.4678
Max Act: 3.2482. Min Act: -0.1700
Data Index: 2875021 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4678. Min Range: -3.4678
Max Act: 3.2168. Min Act: -0.1700
Data Index: 8270945 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4678. Min Range: -3.4678
Max Act: 3.2482. Min Act: -0.1700
Data Index: 2166117 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4678. Min Range: -3.4678
Max Act: 3.2168. Min Act: -0.1700
Data Index: 1039860 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4678. Min Range: -3.4678
Max Act: 3.2010. Min Act: -0.1700
Data Index: 8108683 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4678. Min Range: -3.4678
Max Act: 3.2010. Min Act: -0.1700
Data Index: 175324 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4678. Min Range: -3.4678
Max Act: 3.2010. Min Act: -0.1700
Data Index: 4250054 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4678. Min Range: -3.4678
Max Act: 3.2010. Min Act: -0.1700
Data Index: 6447235 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #19