Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 859 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0868. Min Range: -4.0868
Max Act: 4.0868. Min Act: -0.1700
Data Index: 4174745 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0868. Min Range: -4.0868
Max Act: 3.9930. Min Act: -0.1700
Data Index: 5475037 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0868. Min Range: -4.0868
Max Act: 3.9930. Min Act: -0.1700
Data Index: 5690184 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0868. Min Range: -4.0868
Max Act: 3.9930. Min Act: -0.1700
Data Index: 3273229 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0868. Min Range: -4.0868
Max Act: 3.9930. Min Act: -0.1700
Data Index: 6770474 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0868. Min Range: -4.0868
Max Act: 3.9618. Min Act: -0.1700
Data Index: 5903800 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0868. Min Range: -4.0868
Max Act: 3.9618. Min Act: -0.1700
Data Index: 8069804 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0868. Min Range: -4.0868
Max Act: 3.9618. Min Act: -0.1700
Data Index: 2027505 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0868. Min Range: -4.0868
Max Act: 3.9618. Min Act: -0.1700
Data Index: 3785114 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0868. Min Range: -4.0868
Max Act: 3.9618. Min Act: -0.1700
Data Index: 5962923 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0868. Min Range: -4.0868
Max Act: 3.9618. Min Act: -0.1700
Data Index: 3780047 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0868. Min Range: -4.0868
Max Act: 3.9618. Min Act: -0.1700
Data Index: 414303 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0868. Min Range: -4.0868
Max Act: 3.9618. Min Act: -0.1700
Data Index: 1985675 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0868. Min Range: -4.0868
Max Act: 3.9618. Min Act: -0.1700
Data Index: 6165293 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0868. Min Range: -4.0868
Max Act: 3.9618. Min Act: -0.1700
Data Index: 3097444 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0868. Min Range: -4.0868
Max Act: 3.9618. Min Act: -0.1700
Data Index: 5692366 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0868. Min Range: -4.0868
Max Act: 3.9618. Min Act: -0.1700
Data Index: 5996911 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0868. Min Range: -4.0868
Max Act: 3.9618. Min Act: -0.1700
Data Index: 2172080 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0868. Min Range: -4.0868
Max Act: 3.9618. Min Act: -0.1700
Data Index: 952501 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0868. Min Range: -4.0868
Max Act: 3.9618. Min Act: -0.1700
Data Index: 6937385 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19