Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 495 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9228. Min Range: -6.9228
Max Act: 6.9228. Min Act: -0.1700
Data Index: 201242 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9228. Min Range: -6.9228
Max Act: 6.7978. Min Act: -0.1700
Data Index: 1049582 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9228. Min Range: -6.9228
Max Act: 6.7665. Min Act: -0.1700
Data Index: 1339447 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9228. Min Range: -6.9228
Max Act: 6.7665. Min Act: -0.1700
Data Index: 8096011 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9228. Min Range: -6.9228
Max Act: 6.7665. Min Act: -0.1700
Data Index: 3952756 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9228. Min Range: -6.9228
Max Act: 6.6728. Min Act: -0.1700
Data Index: 6058757 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9228. Min Range: -6.9228
Max Act: 6.6103. Min Act: -0.1700
Data Index: 2545757 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9228. Min Range: -6.9228
Max Act: 6.6103. Min Act: -0.1700
Data Index: 818494 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9228. Min Range: -6.9228
Max Act: 6.5790. Min Act: -0.1700
Data Index: 944094 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9228. Min Range: -6.9228
Max Act: 6.5165. Min Act: -0.1700
Data Index: 3766990 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9228. Min Range: -6.9228
Max Act: 6.5478. Min Act: -0.1700
Data Index: 4383369 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9228. Min Range: -6.9228
Max Act: 6.5478. Min Act: -0.1700
Data Index: 5495808 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9228. Min Range: -6.9228
Max Act: 6.5165. Min Act: -0.1700
Data Index: 6466259 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9228. Min Range: -6.9228
Max Act: 6.5165. Min Act: -0.1700
Data Index: 7397384 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9228. Min Range: -6.9228
Max Act: 6.4853. Min Act: -0.1700
Data Index: 8626647 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9228. Min Range: -6.9228
Max Act: 6.4853. Min Act: -0.1700
Data Index: 6250333 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9228. Min Range: -6.9228
Max Act: 6.4540. Min Act: -0.1700
Data Index: 7036045 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9228. Min Range: -6.9228
Max Act: 6.4540. Min Act: -0.1700
Data Index: 7800312 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9228. Min Range: -6.9228
Max Act: 6.4228. Min Act: -0.1700
Data Index: 1908854 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9228. Min Range: -6.9228
Max Act: 6.4228. Min Act: -0.1700
Data Index: 3053265 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19