Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3975 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1568. Min Range: -4.1568
Max Act: 4.1568. Min Act: -0.1700
Data Index: 881444 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1568. Min Range: -4.1568
Max Act: 4.0005. Min Act: -0.1700
Data Index: 5905053 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1568. Min Range: -4.1568
Max Act: 3.9693. Min Act: -0.1700
Data Index: 8648056 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1568. Min Range: -4.1568
Max Act: 3.8755. Min Act: -0.1700
Data Index: 2018114 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1568. Min Range: -4.1568
Max Act: 3.9067. Min Act: -0.1700
Data Index: 3243461 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1568. Min Range: -4.1568
Max Act: 3.9067. Min Act: -0.1700
Data Index: 8491844 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1568. Min Range: -4.1568
Max Act: 3.8755. Min Act: -0.1700
Data Index: 7793960 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1568. Min Range: -4.1568
Max Act: 3.8755. Min Act: -0.1700
Data Index: 1000296 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1568. Min Range: -4.1568
Max Act: 3.8129. Min Act: -0.1700
Data Index: 7364499 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1568. Min Range: -4.1568
Max Act: 3.8129. Min Act: -0.1700
Data Index: 7042174 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1568. Min Range: -4.1568
Max Act: 3.7817. Min Act: -0.1700
Data Index: 2055655 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1568. Min Range: -4.1568
Max Act: 3.8129. Min Act: -0.1700
Data Index: 6816878 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1568. Min Range: -4.1568
Max Act: 3.8129. Min Act: -0.1700
Data Index: 5063311 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1568. Min Range: -4.1568
Max Act: 3.7817. Min Act: -0.1700
Data Index: 7734818 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1568. Min Range: -4.1568
Max Act: 3.7817. Min Act: -0.1700
Data Index: 491908 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1568. Min Range: -4.1568
Max Act: 3.7817. Min Act: -0.1700
Data Index: 47797 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1568. Min Range: -4.1568
Max Act: 3.7817. Min Act: -0.1700
Data Index: 4887245 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1568. Min Range: -4.1568
Max Act: 3.7817. Min Act: -0.1700
Data Index: 1884767 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1568. Min Range: -4.1568
Max Act: 3.7817. Min Act: -0.1700
Data Index: 8399829 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1568. Min Range: -4.1568
Max Act: 3.7504. Min Act: -0.1700
Data Index: 7816755 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #19