Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1532 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5071. Min Range: -4.5071
Max Act: 4.5071. Min Act: -0.1700
Data Index: 8631441 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5071. Min Range: -4.5071
Max Act: 4.3821. Min Act: -0.1700
Data Index: 3101047 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5071. Min Range: -4.5071
Max Act: 4.3508. Min Act: -0.1700
Data Index: 2370662 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5071. Min Range: -4.5071
Max Act: 4.3821. Min Act: -0.1700
Data Index: 5407652 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5071. Min Range: -4.5071
Max Act: 4.3196. Min Act: -0.1700
Data Index: 6244876 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5071. Min Range: -4.5071
Max Act: 4.3821. Min Act: -0.1700
Data Index: 2052696 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5071. Min Range: -4.5071
Max Act: 4.3508. Min Act: -0.1700
Data Index: 1035655 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5071. Min Range: -4.5071
Max Act: 4.3196. Min Act: -0.1700
Data Index: 1232133 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5071. Min Range: -4.5071
Max Act: 4.2883. Min Act: -0.1700
Data Index: 2740195 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5071. Min Range: -4.5071
Max Act: 4.2571. Min Act: -0.1700
Data Index: 6986922 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5071. Min Range: -4.5071
Max Act: 4.2883. Min Act: -0.1700
Data Index: 1339921 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5071. Min Range: -4.5071
Max Act: 4.2883. Min Act: -0.1700
Data Index: 1115170 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5071. Min Range: -4.5071
Max Act: 4.2883. Min Act: -0.1700
Data Index: 1495715 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5071. Min Range: -4.5071
Max Act: 4.2883. Min Act: -0.1700
Data Index: 2494709 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5071. Min Range: -4.5071
Max Act: 4.2883. Min Act: -0.1700
Data Index: 2399944 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5071. Min Range: -4.5071
Max Act: 4.2571. Min Act: -0.1700
Data Index: 6048066 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5071. Min Range: -4.5071
Max Act: 4.3196. Min Act: -0.1700
Data Index: 1399790 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5071. Min Range: -4.5071
Max Act: 4.2571. Min Act: -0.1700
Data Index: 1292283 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5071. Min Range: -4.5071
Max Act: 4.2883. Min Act: -0.1700
Data Index: 4379486 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5071. Min Range: -4.5071
Max Act: 4.2571. Min Act: -0.1700
Data Index: 6859881 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19