Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4253 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2634. Min Range: -8.2634
Max Act: 8.2634. Min Act: -0.1700
Data Index: 2988129 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2634. Min Range: -8.2634
Max Act: 7.9509. Min Act: -0.1700
Data Index: 805842 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2634. Min Range: -8.2634
Max Act: 7.8884. Min Act: -0.1700
Data Index: 2584394 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2634. Min Range: -8.2634
Max Act: 7.9509. Min Act: -0.1700
Data Index: 19783 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2634. Min Range: -8.2634
Max Act: 7.9509. Min Act: -0.1700
Data Index: 6313651 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2634. Min Range: -8.2634
Max Act: 7.7634. Min Act: -0.1700
Data Index: 2551606 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2634. Min Range: -8.2634
Max Act: 7.7009. Min Act: -0.1700
Data Index: 2316653 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2634. Min Range: -8.2634
Max Act: 7.7009. Min Act: -0.1700
Data Index: 7972800 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2634. Min Range: -8.2634
Max Act: 7.7009. Min Act: -0.1700
Data Index: 6900848 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2634. Min Range: -8.2634
Max Act: 7.6384. Min Act: -0.1700
Data Index: 8689398 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2634. Min Range: -8.2634
Max Act: 7.6384. Min Act: -0.1700
Data Index: 5298659 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2634. Min Range: -8.2634
Max Act: 7.6384. Min Act: -0.1700
Data Index: 594409 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2634. Min Range: -8.2634
Max Act: 7.6384. Min Act: -0.1700
Data Index: 4801781 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2634. Min Range: -8.2634
Max Act: 7.6384. Min Act: -0.1700
Data Index: 7954294 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2634. Min Range: -8.2634
Max Act: 7.5759. Min Act: -0.1700
Data Index: 2108691 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2634. Min Range: -8.2634
Max Act: 7.5759. Min Act: -0.1700
Data Index: 5233376 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2634. Min Range: -8.2634
Max Act: 7.5759. Min Act: -0.1700
Data Index: 4875245 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2634. Min Range: -8.2634
Max Act: 7.4822. Min Act: -0.1700
Data Index: 2959483 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2634. Min Range: -8.2634
Max Act: 7.5134. Min Act: -0.1700
Data Index: 5944353 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2634. Min Range: -8.2634
Max Act: 7.5134. Min Act: -0.1700
Data Index: 6640807 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #19