Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2952 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6186. Min Range: -4.6186
Max Act: 4.6186. Min Act: -0.1700
Data Index: 2904345 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6186. Min Range: -4.6186
Max Act: 4.6186. Min Act: -0.1700
Data Index: 7398666 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6186. Min Range: -4.6186
Max Act: 4.6186. Min Act: -0.1700
Data Index: 3797775 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6186. Min Range: -4.6186
Max Act: 4.6186. Min Act: -0.1700
Data Index: 8461044 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6186. Min Range: -4.6186
Max Act: 4.6186. Min Act: -0.1700
Data Index: 3913235 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6186. Min Range: -4.6186
Max Act: 4.6186. Min Act: -0.1700
Data Index: 6658131 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6186. Min Range: -4.6186
Max Act: 4.6186. Min Act: -0.1700
Data Index: 6043185 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6186. Min Range: -4.6186
Max Act: 4.6186. Min Act: -0.1700
Data Index: 8652499 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6186. Min Range: -4.6186
Max Act: 4.6186. Min Act: -0.1700
Data Index: 4014816 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6186. Min Range: -4.6186
Max Act: 4.1498. Min Act: -0.1700
Data Index: 6940600 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6186. Min Range: -4.6186
Max Act: 4.1498. Min Act: -0.1700
Data Index: 4226584 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6186. Min Range: -4.6186
Max Act: 4.1498. Min Act: -0.1700
Data Index: 6449288 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6186. Min Range: -4.6186
Max Act: 4.1498. Min Act: -0.1700
Data Index: 6720136 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6186. Min Range: -4.6186
Max Act: 4.1498. Min Act: -0.1700
Data Index: 1285273 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6186. Min Range: -4.6186
Max Act: 4.1498. Min Act: -0.1700
Data Index: 8395866 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6186. Min Range: -4.6186
Max Act: 4.1498. Min Act: -0.1700
Data Index: 22865 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6186. Min Range: -4.6186
Max Act: 4.1498. Min Act: -0.1700
Data Index: 1631984 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6186. Min Range: -4.6186
Max Act: 4.1498. Min Act: -0.1700
Data Index: 3470465 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6186. Min Range: -4.6186
Max Act: 4.1498. Min Act: -0.1700
Data Index: 4589946 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6186. Min Range: -4.6186
Max Act: 4.1186. Min Act: -0.1700
Data Index: 8574878 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19