Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2317 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5575. Min Range: -5.5575
Max Act: 5.5575. Min Act: -0.1700
Data Index: 2836864 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5575. Min Range: -5.5575
Max Act: 5.5575. Min Act: -0.1700
Data Index: 2477689 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5575. Min Range: -5.5575
Max Act: 5.5262. Min Act: -0.1700
Data Index: 5794853 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5575. Min Range: -5.5575
Max Act: 5.4012. Min Act: -0.1700
Data Index: 3089323 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5575. Min Range: -5.5575
Max Act: 5.3075. Min Act: -0.1700
Data Index: 1236712 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5575. Min Range: -5.5575
Max Act: 5.3075. Min Act: -0.1700
Data Index: 1883603 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5575. Min Range: -5.5575
Max Act: 5.2762. Min Act: -0.1700
Data Index: 3957885 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5575. Min Range: -5.5575
Max Act: 5.2762. Min Act: -0.1700
Data Index: 7839228 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5575. Min Range: -5.5575
Max Act: 5.2450. Min Act: -0.1700
Data Index: 255815 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5575. Min Range: -5.5575
Max Act: 5.2137. Min Act: -0.1700
Data Index: 2321333 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5575. Min Range: -5.5575
Max Act: 5.2450. Min Act: -0.1700
Data Index: 7999590 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5575. Min Range: -5.5575
Max Act: 5.2762. Min Act: -0.1700
Data Index: 395358 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5575. Min Range: -5.5575
Max Act: 5.2137. Min Act: -0.1700
Data Index: 4136008 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5575. Min Range: -5.5575
Max Act: 5.1825. Min Act: -0.1700
Data Index: 5588893 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5575. Min Range: -5.5575
Max Act: 5.1512. Min Act: -0.1700
Data Index: 6015762 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5575. Min Range: -5.5575
Max Act: 5.1512. Min Act: -0.1700
Data Index: 5221460 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5575. Min Range: -5.5575
Max Act: 5.1200. Min Act: -0.1700
Data Index: 8619569 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5575. Min Range: -5.5575
Max Act: 5.0575. Min Act: -0.1700
Data Index: 1825155 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5575. Min Range: -5.5575
Max Act: 5.0887. Min Act: -0.1700
Data Index: 5678376 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5575. Min Range: -5.5575
Max Act: 5.0262. Min Act: -0.1700
Data Index: 3200596 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19