Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2695 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9779. Min Range: -5.9779
Max Act: 5.9779. Min Act: -0.1700
Data Index: 582437 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9779. Min Range: -5.9779
Max Act: 5.9154. Min Act: -0.1700
Data Index: 5196519 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9779. Min Range: -5.9779
Max Act: 5.9154. Min Act: -0.1700
Data Index: 6540798 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9779. Min Range: -5.9779
Max Act: 5.7904. Min Act: -0.1700
Data Index: 5487517 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9779. Min Range: -5.9779
Max Act: 5.7904. Min Act: -0.1700
Data Index: 4358321 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9779. Min Range: -5.9779
Max Act: 5.6966. Min Act: -0.1700
Data Index: 5164728 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9779. Min Range: -5.9779
Max Act: 5.6966. Min Act: -0.1700
Data Index: 2431243 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9779. Min Range: -5.9779
Max Act: 5.6654. Min Act: -0.1700
Data Index: 6038217 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9779. Min Range: -5.9779
Max Act: 5.6654. Min Act: -0.1700
Data Index: 7333403 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9779. Min Range: -5.9779
Max Act: 5.6654. Min Act: -0.1700
Data Index: 8239970 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9779. Min Range: -5.9779
Max Act: 5.6654. Min Act: -0.1700
Data Index: 7417580 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9779. Min Range: -5.9779
Max Act: 5.6029. Min Act: -0.1700
Data Index: 5532598 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9779. Min Range: -5.9779
Max Act: 5.5716. Min Act: -0.1700
Data Index: 6886790 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9779. Min Range: -5.9779
Max Act: 5.6029. Min Act: -0.1700
Data Index: 7879756 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9779. Min Range: -5.9779
Max Act: 5.5716. Min Act: -0.1700
Data Index: 4724909 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9779. Min Range: -5.9779
Max Act: 5.5404. Min Act: -0.1700
Data Index: 3048014 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9779. Min Range: -5.9779
Max Act: 5.5091. Min Act: -0.1700
Data Index: 4475958 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9779. Min Range: -5.9779
Max Act: 5.5091. Min Act: -0.1700
Data Index: 2303203 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9779. Min Range: -5.9779
Max Act: 5.5091. Min Act: -0.1700
Data Index: 3368512 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9779. Min Range: -5.9779
Max Act: 5.5404. Min Act: -0.1700
Data Index: 7901028 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19