Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 37 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9710. Min Range: -2.9710
Max Act: 2.9710. Min Act: -0.1700
Data Index: 2498592 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9710. Min Range: -2.9710
Max Act: 2.9552. Min Act: -0.1700
Data Index: 7204601 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9710. Min Range: -2.9710
Max Act: 2.8918. Min Act: -0.1700
Data Index: 642792 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9710. Min Range: -2.9710
Max Act: 2.8918. Min Act: -0.1700
Data Index: 3854981 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9710. Min Range: -2.9710
Max Act: 2.8918. Min Act: -0.1700
Data Index: 33623 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9710. Min Range: -2.9710
Max Act: 2.8918. Min Act: -0.1700
Data Index: 5071471 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9710. Min Range: -2.9710
Max Act: 2.8918. Min Act: -0.1700
Data Index: 3854141 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9710. Min Range: -2.9710
Max Act: 2.8918. Min Act: -0.1700
Data Index: 330159 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9710. Min Range: -2.9710
Max Act: 2.8918. Min Act: -0.1700
Data Index: 2113211 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9710. Min Range: -2.9710
Max Act: 2.8918. Min Act: -0.1700
Data Index: 672063 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9710. Min Range: -2.9710
Max Act: 2.8918. Min Act: -0.1700
Data Index: 1887303 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9710. Min Range: -2.9710
Max Act: 2.8918. Min Act: -0.1700
Data Index: 3832864 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9710. Min Range: -2.9710
Max Act: 2.8918. Min Act: -0.1700
Data Index: 427045 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9710. Min Range: -2.9710
Max Act: 2.8918. Min Act: -0.1700
Data Index: 3498087 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9710. Min Range: -2.9710
Max Act: 2.8918. Min Act: -0.1700
Data Index: 630349 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9710. Min Range: -2.9710
Max Act: 2.8918. Min Act: -0.1700
Data Index: 3294851 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9710. Min Range: -2.9710
Max Act: 2.8918. Min Act: -0.1700
Data Index: 2615753 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9710. Min Range: -2.9710
Max Act: 2.8918. Min Act: -0.1700
Data Index: 2543777 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9710. Min Range: -2.9710
Max Act: 2.8918. Min Act: -0.1700
Data Index: 639616 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9710. Min Range: -2.9710
Max Act: 2.8918. Min Act: -0.1700
Data Index: 5050575 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19