Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 331 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.0482. Min Range: -8.0482
Max Act: 8.0482. Min Act: -0.1700
Data Index: 3114019 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0482. Min Range: -8.0482
Max Act: 7.9857. Min Act: -0.1700
Data Index: 4388856 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0482. Min Range: -8.0482
Max Act: 7.9232. Min Act: -0.1700
Data Index: 6591245 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0482. Min Range: -8.0482
Max Act: 7.8919. Min Act: -0.1700
Data Index: 1520560 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0482. Min Range: -8.0482
Max Act: 7.8607. Min Act: -0.1700
Data Index: 4732580 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0482. Min Range: -8.0482
Max Act: 7.8919. Min Act: -0.1700
Data Index: 2988594 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0482. Min Range: -8.0482
Max Act: 7.8607. Min Act: -0.1700
Data Index: 8080765 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0482. Min Range: -8.0482
Max Act: 7.8294. Min Act: -0.1700
Data Index: 473063 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0482. Min Range: -8.0482
Max Act: 7.7982. Min Act: -0.1700
Data Index: 559672 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0482. Min Range: -8.0482
Max Act: 7.7669. Min Act: -0.1700
Data Index: 4631058 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0482. Min Range: -8.0482
Max Act: 7.7669. Min Act: -0.1700
Data Index: 5969797 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0482. Min Range: -8.0482
Max Act: 7.7669. Min Act: -0.1700
Data Index: 8771172 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0482. Min Range: -8.0482
Max Act: 7.7669. Min Act: -0.1700
Data Index: 2898136 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0482. Min Range: -8.0482
Max Act: 7.7669. Min Act: -0.1700
Data Index: 2199572 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0482. Min Range: -8.0482
Max Act: 7.7669. Min Act: -0.1700
Data Index: 5889688 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0482. Min Range: -8.0482
Max Act: 7.7357. Min Act: -0.1700
Data Index: 5270633 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0482. Min Range: -8.0482
Max Act: 7.7357. Min Act: -0.1700
Data Index: 229522 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0482. Min Range: -8.0482
Max Act: 7.7357. Min Act: -0.1700
Data Index: 5656621 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0482. Min Range: -8.0482
Max Act: 7.7357. Min Act: -0.1700
Data Index: 7063191 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0482. Min Range: -8.0482
Max Act: 7.7044. Min Act: -0.1700
Data Index: 2839796 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19