Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3967 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.6851. Min Range: -8.6851
Max Act: 8.6851. Min Act: -0.1700
Data Index: 8026253 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6851. Min Range: -8.6851
Max Act: 8.5601. Min Act: -0.1700
Data Index: 4416064 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6851. Min Range: -8.6851
Max Act: 7.9976. Min Act: -0.1700
Data Index: 7596231 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6851. Min Range: -8.6851
Max Act: 7.8726. Min Act: -0.1700
Data Index: 3301001 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6851. Min Range: -8.6851
Max Act: 7.8101. Min Act: -0.1700
Data Index: 1286541 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6851. Min Range: -8.6851
Max Act: 7.7789. Min Act: -0.1700
Data Index: 7792789 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6851. Min Range: -8.6851
Max Act: 7.7476. Min Act: -0.1700
Data Index: 1801495 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6851. Min Range: -8.6851
Max Act: 7.7164. Min Act: -0.1700
Data Index: 4141773 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6851. Min Range: -8.6851
Max Act: 7.6851. Min Act: -0.1700
Data Index: 7873033 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6851. Min Range: -8.6851
Max Act: 7.7164. Min Act: -0.1700
Data Index: 2399695 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6851. Min Range: -8.6851
Max Act: 7.6539. Min Act: -0.1700
Data Index: 938314 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6851. Min Range: -8.6851
Max Act: 7.7164. Min Act: -0.1700
Data Index: 4407799 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6851. Min Range: -8.6851
Max Act: 7.6226. Min Act: -0.1700
Data Index: 2714634 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6851. Min Range: -8.6851
Max Act: 7.5914. Min Act: -0.1700
Data Index: 8112976 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6851. Min Range: -8.6851
Max Act: 7.5914. Min Act: -0.1700
Data Index: 6229985 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6851. Min Range: -8.6851
Max Act: 7.5914. Min Act: -0.1700
Data Index: 4071315 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6851. Min Range: -8.6851
Max Act: 7.5914. Min Act: -0.1700
Data Index: 3206418 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6851. Min Range: -8.6851
Max Act: 7.6226. Min Act: -0.1700
Data Index: 4382217 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6851. Min Range: -8.6851
Max Act: 7.5914. Min Act: -0.1700
Data Index: 7232217 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6851. Min Range: -8.6851
Max Act: 7.5289. Min Act: -0.1700
Data Index: 7706318 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #19