Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3122 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6773. Min Range: -6.6773
Max Act: 6.6773. Min Act: -0.1700
Data Index: 3559467 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6773. Min Range: -6.6773
Max Act: 6.6148. Min Act: -0.1700
Data Index: 6757629 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6773. Min Range: -6.6773
Max Act: 6.5210. Min Act: -0.1700
Data Index: 1609511 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6773. Min Range: -6.6773
Max Act: 6.5210. Min Act: -0.1700
Data Index: 1012978 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6773. Min Range: -6.6773
Max Act: 6.4898. Min Act: -0.1700
Data Index: 3230093 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6773. Min Range: -6.6773
Max Act: 6.4585. Min Act: -0.1694
Data Index: 4794854 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6773. Min Range: -6.6773
Max Act: 6.4585. Min Act: -0.1700
Data Index: 2970816 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6773. Min Range: -6.6773
Max Act: 6.4585. Min Act: -0.1700
Data Index: 3230095 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6773. Min Range: -6.6773
Max Act: 6.4585. Min Act: -0.1700
Data Index: 476126 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6773. Min Range: -6.6773
Max Act: 6.4273. Min Act: -0.1700
Data Index: 369813 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6773. Min Range: -6.6773
Max Act: 6.4273. Min Act: -0.1700
Data Index: 3422916 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6773. Min Range: -6.6773
Max Act: 6.4273. Min Act: -0.1700
Data Index: 6696847 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6773. Min Range: -6.6773
Max Act: 6.4273. Min Act: -0.1700
Data Index: 3734674 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6773. Min Range: -6.6773
Max Act: 6.3960. Min Act: -0.1700
Data Index: 6934888 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6773. Min Range: -6.6773
Max Act: 6.3960. Min Act: -0.1700
Data Index: 5084842 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6773. Min Range: -6.6773
Max Act: 6.3648. Min Act: -0.1700
Data Index: 6628347 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6773. Min Range: -6.6773
Max Act: 6.3960. Min Act: -0.1700
Data Index: 2915593 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6773. Min Range: -6.6773
Max Act: 6.3960. Min Act: -0.1700
Data Index: 7928797 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6773. Min Range: -6.6773
Max Act: 6.3960. Min Act: -0.1700
Data Index: 2970815 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6773. Min Range: -6.6773
Max Act: 6.3648. Min Act: -0.1700
Data Index: 1294639 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19