Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1804 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8883. Min Range: -5.8883
Max Act: 5.8883. Min Act: -0.1700
Data Index: 3973845 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8883. Min Range: -5.8883
Max Act: 5.8258. Min Act: -0.1700
Data Index: 2400155 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8883. Min Range: -5.8883
Max Act: 5.8258. Min Act: -0.1700
Data Index: 1589292 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8883. Min Range: -5.8883
Max Act: 5.7946. Min Act: -0.1700
Data Index: 8174880 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8883. Min Range: -5.8883
Max Act: 5.7633. Min Act: -0.1700
Data Index: 8414093 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8883. Min Range: -5.8883
Max Act: 5.7633. Min Act: -0.1696
Data Index: 2529154 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8883. Min Range: -5.8883
Max Act: 5.7633. Min Act: -0.1693
Data Index: 8276990 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8883. Min Range: -5.8883
Max Act: 5.7008. Min Act: -0.1700
Data Index: 6808149 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8883. Min Range: -5.8883
Max Act: 5.6696. Min Act: -0.1700
Data Index: 4184073 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8883. Min Range: -5.8883
Max Act: 5.6696. Min Act: -0.1700
Data Index: 1911356 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8883. Min Range: -5.8883
Max Act: 5.6696. Min Act: -0.1699
Data Index: 5573713 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8883. Min Range: -5.8883
Max Act: 5.6696. Min Act: -0.1700
Data Index: 8758192 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8883. Min Range: -5.8883
Max Act: 5.6696. Min Act: -0.1700
Data Index: 8508600 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8883. Min Range: -5.8883
Max Act: 5.6696. Min Act: -0.1698
Data Index: 3662891 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8883. Min Range: -5.8883
Max Act: 5.6696. Min Act: -0.1700
Data Index: 7862120 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8883. Min Range: -5.8883
Max Act: 5.7008. Min Act: -0.1700
Data Index: 2969203 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8883. Min Range: -5.8883
Max Act: 5.6696. Min Act: -0.1700
Data Index: 3163439 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8883. Min Range: -5.8883
Max Act: 5.6383. Min Act: -0.1700
Data Index: 2562268 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8883. Min Range: -5.8883
Max Act: 5.6383. Min Act: -0.1700
Data Index: 3813859 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8883. Min Range: -5.8883
Max Act: 5.6383. Min Act: -0.1700
Data Index: 3758318 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19