Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 195 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3880. Min Range: -3.3880
Max Act: 3.3880. Min Act: -0.1700
Data Index: 2701983 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3880. Min Range: -3.3880
Max Act: 3.3880. Min Act: -0.1700
Data Index: 5705619 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3880. Min Range: -3.3880
Max Act: 3.3880. Min Act: -0.1700
Data Index: 6137754 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3880. Min Range: -3.3880
Max Act: 3.3566. Min Act: -0.1700
Data Index: 8811702 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3880. Min Range: -3.3880
Max Act: 3.2782. Min Act: -0.1700
Data Index: 4148620 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3880. Min Range: -3.3880
Max Act: 3.2782. Min Act: -0.1700
Data Index: 3799812 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3880. Min Range: -3.3880
Max Act: 3.2310. Min Act: -0.1700
Data Index: 5498775 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3880. Min Range: -3.3880
Max Act: 3.2468. Min Act: -0.1700
Data Index: 3997071 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3880. Min Range: -3.3880
Max Act: 3.2153. Min Act: -0.1700
Data Index: 6343365 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3880. Min Range: -3.3880
Max Act: 3.2310. Min Act: -0.1700
Data Index: 8566040 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3880. Min Range: -3.3880
Max Act: 3.2153. Min Act: -0.1700
Data Index: 141264 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3880. Min Range: -3.3880
Max Act: 3.1996. Min Act: -0.1700
Data Index: 224837 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3880. Min Range: -3.3880
Max Act: 3.1996. Min Act: -0.1700
Data Index: 1916750 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3880. Min Range: -3.3880
Max Act: 3.1996. Min Act: -0.1700
Data Index: 7097208 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3880. Min Range: -3.3880
Max Act: 3.1524. Min Act: -0.1700
Data Index: 4280280 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3880. Min Range: -3.3880
Max Act: 3.1839. Min Act: -0.1700
Data Index: 7969403 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3880. Min Range: -3.3880
Max Act: 3.1681. Min Act: -0.1700
Data Index: 3289176 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3880. Min Range: -3.3880
Max Act: 3.1524. Min Act: -0.1700
Data Index: 7851192 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3880. Min Range: -3.3880
Max Act: 3.1524. Min Act: -0.1700
Data Index: 6039373 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3880. Min Range: -3.3880
Max Act: 3.1681. Min Act: -0.1700
Data Index: 1617401 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19