Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3616 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0094. Min Range: -6.0094
Max Act: 6.0094. Min Act: -0.1700
Data Index: 3561851 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0094. Min Range: -6.0094
Max Act: 5.9157. Min Act: -0.1700
Data Index: 5405861 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0094. Min Range: -6.0094
Max Act: 5.8844. Min Act: -0.1700
Data Index: 7706772 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0094. Min Range: -6.0094
Max Act: 5.7907. Min Act: -0.1700
Data Index: 7146000 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0094. Min Range: -6.0094
Max Act: 5.7594. Min Act: -0.1700
Data Index: 4079499 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0094. Min Range: -6.0094
Max Act: 5.7594. Min Act: -0.1700
Data Index: 3646621 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0094. Min Range: -6.0094
Max Act: 5.7282. Min Act: -0.1700
Data Index: 7318979 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0094. Min Range: -6.0094
Max Act: 5.6969. Min Act: -0.1700
Data Index: 6014384 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0094. Min Range: -6.0094
Max Act: 5.6969. Min Act: -0.1700
Data Index: 3657019 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0094. Min Range: -6.0094
Max Act: 5.6969. Min Act: -0.1700
Data Index: 3657006 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0094. Min Range: -6.0094
Max Act: 5.6657. Min Act: -0.1700
Data Index: 4840256 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0094. Min Range: -6.0094
Max Act: 5.6344. Min Act: -0.1700
Data Index: 2655241 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0094. Min Range: -6.0094
Max Act: 5.6344. Min Act: -0.1700
Data Index: 4157956 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0094. Min Range: -6.0094
Max Act: 5.6344. Min Act: -0.1700
Data Index: 7515203 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0094. Min Range: -6.0094
Max Act: 5.6344. Min Act: -0.1700
Data Index: 1640727 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0094. Min Range: -6.0094
Max Act: 5.6657. Min Act: -0.1700
Data Index: 5310221 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0094. Min Range: -6.0094
Max Act: 5.6032. Min Act: -0.1700
Data Index: 660629 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0094. Min Range: -6.0094
Max Act: 5.6032. Min Act: -0.1700
Data Index: 1969098 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0094. Min Range: -6.0094
Max Act: 5.6032. Min Act: -0.1700
Data Index: 6067047 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0094. Min Range: -6.0094
Max Act: 5.6032. Min Act: -0.1700
Data Index: 4959640 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19