Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2754 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5709. Min Range: -5.5709
Max Act: 5.5709. Min Act: -0.1700
Data Index: 2181773 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5709. Min Range: -5.5709
Max Act: 5.1959. Min Act: -0.1700
Data Index: 5349290 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5709. Min Range: -5.5709
Max Act: 5.1334. Min Act: -0.1700
Data Index: 2073517 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5709. Min Range: -5.5709
Max Act: 5.1021. Min Act: -0.1700
Data Index: 1204781 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5709. Min Range: -5.5709
Max Act: 5.0709. Min Act: -0.1700
Data Index: 6809857 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5709. Min Range: -5.5709
Max Act: 5.1021. Min Act: -0.1700
Data Index: 6501681 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5709. Min Range: -5.5709
Max Act: 5.0396. Min Act: -0.1700
Data Index: 4184614 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5709. Min Range: -5.5709
Max Act: 5.0396. Min Act: -0.1700
Data Index: 985282 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5709. Min Range: -5.5709
Max Act: 5.0084. Min Act: -0.1700
Data Index: 2873671 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5709. Min Range: -5.5709
Max Act: 5.0084. Min Act: -0.1700
Data Index: 7333297 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5709. Min Range: -5.5709
Max Act: 5.0084. Min Act: -0.1700
Data Index: 3260408 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5709. Min Range: -5.5709
Max Act: 4.9771. Min Act: -0.1700
Data Index: 4177270 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5709. Min Range: -5.5709
Max Act: 4.9771. Min Act: -0.1700
Data Index: 3099758 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5709. Min Range: -5.5709
Max Act: 4.9771. Min Act: -0.1700
Data Index: 987856 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5709. Min Range: -5.5709
Max Act: 4.9771. Min Act: -0.1700
Data Index: 7609382 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5709. Min Range: -5.5709
Max Act: 4.9771. Min Act: -0.1700
Data Index: 2841593 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5709. Min Range: -5.5709
Max Act: 4.9459. Min Act: -0.1700
Data Index: 6730491 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5709. Min Range: -5.5709
Max Act: 4.9459. Min Act: -0.1700
Data Index: 4975959 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5709. Min Range: -5.5709
Max Act: 4.9459. Min Act: -0.1700
Data Index: 2784526 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5709. Min Range: -5.5709
Max Act: 4.9146. Min Act: -0.1700
Data Index: 4393345 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #19