Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5738 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0718. Min Range: -8.0718
Max Act: 8.0718. Min Act: -0.1700
Data Index: 6033027 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0718. Min Range: -8.0718
Max Act: 8.0406. Min Act: -0.1700
Data Index: 2357909 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0718. Min Range: -8.0718
Max Act: 7.9156. Min Act: -0.1700
Data Index: 3329677 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0718. Min Range: -8.0718
Max Act: 7.8531. Min Act: -0.1700
Data Index: 2711043 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0718. Min Range: -8.0718
Max Act: 7.8531. Min Act: -0.1700
Data Index: 6075333 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0718. Min Range: -8.0718
Max Act: 7.8218. Min Act: -0.1700
Data Index: 4906184 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0718. Min Range: -8.0718
Max Act: 7.7906. Min Act: -0.1700
Data Index: 1932639 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0718. Min Range: -8.0718
Max Act: 7.7281. Min Act: -0.1700
Data Index: 8003480 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0718. Min Range: -8.0718
Max Act: 7.7281. Min Act: -0.1700
Data Index: 8430078 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0718. Min Range: -8.0718
Max Act: 7.6968. Min Act: -0.1700
Data Index: 2884896 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0718. Min Range: -8.0718
Max Act: 7.6656. Min Act: -0.1700
Data Index: 283020 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0718. Min Range: -8.0718
Max Act: 7.6656. Min Act: -0.1700
Data Index: 2618708 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0718. Min Range: -8.0718
Max Act: 7.6031. Min Act: -0.1700
Data Index: 283019 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0718. Min Range: -8.0718
Max Act: 7.6343. Min Act: -0.1700
Data Index: 7839999 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0718. Min Range: -8.0718
Max Act: 7.6343. Min Act: -0.1700
Data Index: 1932638 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0718. Min Range: -8.0718
Max Act: 7.6343. Min Act: -0.1700
Data Index: 8761051 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0718. Min Range: -8.0718
Max Act: 7.6031. Min Act: -0.1700
Data Index: 6296372 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0718. Min Range: -8.0718
Max Act: 7.5718. Min Act: -0.1700
Data Index: 5217975 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0718. Min Range: -8.0718
Max Act: 7.6031. Min Act: -0.1700
Data Index: 3698736 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0718. Min Range: -8.0718
Max Act: 7.5718. Min Act: -0.1700
Data Index: 5554675 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #19