Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 722 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.7396. Min Range: -1.7396
Max Act: 1.7396. Min Act: -0.1700
Data Index: 1914523 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7396. Min Range: -1.7396
Max Act: 1.7223. Min Act: -0.1700
Data Index: 5664264 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7396. Min Range: -1.7396
Max Act: 1.7050. Min Act: -0.0864
Data Index: 1923233 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7396. Min Range: -1.7396
Max Act: 1.6876. Min Act: -0.1700
Data Index: 620789 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7396. Min Range: -1.7396
Max Act: 1.6876. Min Act: -0.0873
Data Index: 5957911 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7396. Min Range: -1.7396
Max Act: 1.6529. Min Act: -0.1337
Data Index: 4500854 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7396. Min Range: -1.7396
Max Act: 1.6529. Min Act: -0.1700
Data Index: 7439454 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7396. Min Range: -1.7396
Max Act: 1.6355. Min Act: -0.1700
Data Index: 4892931 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7396. Min Range: -1.7396
Max Act: 1.6529. Min Act: -0.1700
Data Index: 723582 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7396. Min Range: -1.7396
Max Act: 1.6355. Min Act: -0.1221
Data Index: 4056927 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7396. Min Range: -1.7396
Max Act: 1.6355. Min Act: -0.1700
Data Index: 3048145 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7396. Min Range: -1.7396
Max Act: 1.6355. Min Act: -0.1697
Data Index: 5135606 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7396. Min Range: -1.7396
Max Act: 1.6529. Min Act: -0.0855
Data Index: 8284777 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7396. Min Range: -1.7396
Max Act: 1.6355. Min Act: -0.1699
Data Index: 473191 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7396. Min Range: -1.7396
Max Act: 1.6355. Min Act: -0.1700
Data Index: 4795626 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7396. Min Range: -1.7396
Max Act: 1.6355. Min Act: -0.1700
Data Index: 2208351 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7396. Min Range: -1.7396
Max Act: 1.6355. Min Act: -0.1700
Data Index: 766488 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7396. Min Range: -1.7396
Max Act: 1.6355. Min Act: -0.1071
Data Index: 6355955 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7396. Min Range: -1.7396
Max Act: 1.6355. Min Act: -0.1700
Data Index: 4608855 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7396. Min Range: -1.7396
Max Act: 1.6355. Min Act: -0.1700
Data Index: 1582249 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19