Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3506 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1773. Min Range: -8.1773
Max Act: 8.1773. Min Act: -0.1700
Data Index: 935961 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1773. Min Range: -8.1773
Max Act: 8.1148. Min Act: -0.1700
Data Index: 8724358 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1773. Min Range: -8.1773
Max Act: 8.0210. Min Act: -0.1700
Data Index: 3336449 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1773. Min Range: -8.1773
Max Act: 8.0210. Min Act: -0.1700
Data Index: 1293712 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1773. Min Range: -8.1773
Max Act: 7.9898. Min Act: -0.1700
Data Index: 1296033 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1773. Min Range: -8.1773
Max Act: 7.9585. Min Act: -0.1700
Data Index: 6022013 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1773. Min Range: -8.1773
Max Act: 7.9273. Min Act: -0.1700
Data Index: 5667021 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1773. Min Range: -8.1773
Max Act: 7.8960. Min Act: -0.1700
Data Index: 6004710 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1773. Min Range: -8.1773
Max Act: 7.8335. Min Act: -0.1700
Data Index: 608467 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1773. Min Range: -8.1773
Max Act: 7.8335. Min Act: -0.1700
Data Index: 1218416 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1773. Min Range: -8.1773
Max Act: 7.7398. Min Act: -0.1700
Data Index: 1601346 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1773. Min Range: -8.1773
Max Act: 7.6773. Min Act: -0.1700
Data Index: 7637759 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1773. Min Range: -8.1773
Max Act: 7.6460. Min Act: -0.1700
Data Index: 888760 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1773. Min Range: -8.1773
Max Act: 7.6460. Min Act: -0.1700
Data Index: 6022012 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1773. Min Range: -8.1773
Max Act: 7.5835. Min Act: -0.1700
Data Index: 5559873 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1773. Min Range: -8.1773
Max Act: 7.5523. Min Act: -0.1700
Data Index: 6166028 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1773. Min Range: -8.1773
Max Act: 7.5523. Min Act: -0.1700
Data Index: 3144393 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1773. Min Range: -8.1773
Max Act: 7.5523. Min Act: -0.1700
Data Index: 4805580 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1773. Min Range: -8.1773
Max Act: 7.5210. Min Act: -0.1700
Data Index: 8140375 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1773. Min Range: -8.1773
Max Act: 7.4898. Min Act: -0.1700
Data Index: 3392979 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #19