Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4922 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8562. Min Range: -3.8562
Max Act: 3.8562. Min Act: -0.1700
Data Index: 4916094 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8562. Min Range: -3.8562
Max Act: 3.8249. Min Act: -0.1700
Data Index: 3631147 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8562. Min Range: -3.8562
Max Act: 3.7624. Min Act: -0.1700
Data Index: 5459854 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8562. Min Range: -3.8562
Max Act: 3.7311. Min Act: -0.1700
Data Index: 5696041 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8562. Min Range: -3.8562
Max Act: 3.6685. Min Act: -0.1700
Data Index: 2806320 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8562. Min Range: -3.8562
Max Act: 3.6685. Min Act: -0.1700
Data Index: 8273824 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8562. Min Range: -3.8562
Max Act: 3.6529. Min Act: -0.1700
Data Index: 7674469 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8562. Min Range: -3.8562
Max Act: 3.6216. Min Act: -0.1700
Data Index: 8785826 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8562. Min Range: -3.8562
Max Act: 3.5903. Min Act: -0.1700
Data Index: 3024217 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8562. Min Range: -3.8562
Max Act: 3.5903. Min Act: -0.1700
Data Index: 3639966 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8562. Min Range: -3.8562
Max Act: 3.5903. Min Act: -0.1700
Data Index: 8476476 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8562. Min Range: -3.8562
Max Act: 3.5903. Min Act: -0.1700
Data Index: 164107 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8562. Min Range: -3.8562
Max Act: 3.5746. Min Act: -0.1700
Data Index: 3937548 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8562. Min Range: -3.8562
Max Act: 3.5746. Min Act: -0.1700
Data Index: 2517048 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8562. Min Range: -3.8562
Max Act: 3.5903. Min Act: -0.1700
Data Index: 723000 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8562. Min Range: -3.8562
Max Act: 3.5746. Min Act: -0.1700
Data Index: 1481614 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8562. Min Range: -3.8562
Max Act: 3.5746. Min Act: -0.1700
Data Index: 6402769 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8562. Min Range: -3.8562
Max Act: 3.5433. Min Act: -0.1700
Data Index: 4799023 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8562. Min Range: -3.8562
Max Act: 3.5590. Min Act: -0.1700
Data Index: 4632809 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8562. Min Range: -3.8562
Max Act: 3.5276. Min Act: -0.1700
Data Index: 396523 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #19