Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 912 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4528. Min Range: -6.4528
Max Act: 6.4528. Min Act: -0.1700
Data Index: 8427724 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4528. Min Range: -6.4528
Max Act: 6.4215. Min Act: -0.1700
Data Index: 8605559 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4528. Min Range: -6.4528
Max Act: 6.3590. Min Act: -0.1700
Data Index: 6042476 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4528. Min Range: -6.4528
Max Act: 6.3590. Min Act: -0.1700
Data Index: 321903 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4528. Min Range: -6.4528
Max Act: 6.3278. Min Act: -0.1700
Data Index: 2818131 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4528. Min Range: -6.4528
Max Act: 6.2965. Min Act: -0.1700
Data Index: 5290633 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4528. Min Range: -6.4528
Max Act: 6.2653. Min Act: -0.1700
Data Index: 4352124 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4528. Min Range: -6.4528
Max Act: 6.2653. Min Act: -0.1700
Data Index: 8060404 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4528. Min Range: -6.4528
Max Act: 6.2653. Min Act: -0.1700
Data Index: 735166 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4528. Min Range: -6.4528
Max Act: 6.2653. Min Act: -0.1700
Data Index: 3388898 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4528. Min Range: -6.4528
Max Act: 6.2653. Min Act: -0.1700
Data Index: 7617000 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4528. Min Range: -6.4528
Max Act: 6.2340. Min Act: -0.1700
Data Index: 7704109 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4528. Min Range: -6.4528
Max Act: 6.2340. Min Act: -0.1700
Data Index: 1203555 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4528. Min Range: -6.4528
Max Act: 6.2340. Min Act: -0.1700
Data Index: 4380220 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4528. Min Range: -6.4528
Max Act: 6.2028. Min Act: -0.1700
Data Index: 1102363 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4528. Min Range: -6.4528
Max Act: 6.2340. Min Act: -0.1700
Data Index: 8802744 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4528. Min Range: -6.4528
Max Act: 6.2028. Min Act: -0.1700
Data Index: 4236958 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4528. Min Range: -6.4528
Max Act: 6.2028. Min Act: -0.1700
Data Index: 1450483 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4528. Min Range: -6.4528
Max Act: 6.2028. Min Act: -0.1700
Data Index: 4354536 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4528. Min Range: -6.4528
Max Act: 6.2340. Min Act: -0.1700
Data Index: 8437142 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #19