Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3638 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1681. Min Range: -6.1681
Max Act: 6.1681. Min Act: -0.1700
Data Index: 3965840 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1681. Min Range: -6.1681
Max Act: 6.1056. Min Act: -0.1700
Data Index: 5487008 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1681. Min Range: -6.1681
Max Act: 6.0744. Min Act: -0.1700
Data Index: 5638151 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1681. Min Range: -6.1681
Max Act: 6.0119. Min Act: -0.1700
Data Index: 614074 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1681. Min Range: -6.1681
Max Act: 5.9806. Min Act: -0.1700
Data Index: 2891736 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1681. Min Range: -6.1681
Max Act: 5.9494. Min Act: -0.1700
Data Index: 4869011 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1681. Min Range: -6.1681
Max Act: 5.9181. Min Act: -0.1700
Data Index: 791284 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1681. Min Range: -6.1681
Max Act: 5.9181. Min Act: -0.1700
Data Index: 5395045 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1681. Min Range: -6.1681
Max Act: 5.8869. Min Act: -0.1700
Data Index: 7301168 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1681. Min Range: -6.1681
Max Act: 5.8869. Min Act: -0.1700
Data Index: 4321471 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1681. Min Range: -6.1681
Max Act: 5.8556. Min Act: -0.1696
Data Index: 3557137 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1681. Min Range: -6.1681
Max Act: 5.8556. Min Act: -0.1700
Data Index: 2374601 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1681. Min Range: -6.1681
Max Act: 5.8556. Min Act: -0.1700
Data Index: 3749349 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1681. Min Range: -6.1681
Max Act: 5.8556. Min Act: -0.1700
Data Index: 4930939 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1681. Min Range: -6.1681
Max Act: 5.8869. Min Act: -0.1700
Data Index: 183937 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1681. Min Range: -6.1681
Max Act: 5.8244. Min Act: -0.1700
Data Index: 380059 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1681. Min Range: -6.1681
Max Act: 5.8244. Min Act: -0.1700
Data Index: 8514635 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1681. Min Range: -6.1681
Max Act: 5.8244. Min Act: -0.1700
Data Index: 85556 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1681. Min Range: -6.1681
Max Act: 5.8244. Min Act: -0.1700
Data Index: 1200522 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1681. Min Range: -6.1681
Max Act: 5.7931. Min Act: -0.1700
Data Index: 7262618 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #19