Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1721 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.2769. Min Range: -11.2769
Max Act: 11.2769. Min Act: -0.1700
Data Index: 7904571 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.2769. Min Range: -11.2769
Max Act: 11.2769. Min Act: -0.1700
Data Index: 6033497 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.2769. Min Range: -11.2769
Max Act: 11.1519. Min Act: -0.1700
Data Index: 1353672 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.2769. Min Range: -11.2769
Max Act: 11.0894. Min Act: -0.1700
Data Index: 7175532 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.2769. Min Range: -11.2769
Max Act: 11.0269. Min Act: -0.1700
Data Index: 5360653 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.2769. Min Range: -11.2769
Max Act: 11.0269. Min Act: -0.1700
Data Index: 7928763 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.2769. Min Range: -11.2769
Max Act: 10.9644. Min Act: -0.1700
Data Index: 2934668 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.2769. Min Range: -11.2769
Max Act: 10.9019. Min Act: -0.1700
Data Index: 4999214 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.2769. Min Range: -11.2769
Max Act: 10.9019. Min Act: -0.1700
Data Index: 6318811 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.2769. Min Range: -11.2769
Max Act: 10.8394. Min Act: -0.1700
Data Index: 2855966 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.2769. Min Range: -11.2769
Max Act: 10.7769. Min Act: -0.1700
Data Index: 4099618 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.2769. Min Range: -11.2769
Max Act: 10.7769. Min Act: -0.1700
Data Index: 492165 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.2769. Min Range: -11.2769
Max Act: 10.7769. Min Act: -0.1700
Data Index: 2084408 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.2769. Min Range: -11.2769
Max Act: 10.7769. Min Act: -0.1700
Data Index: 2855962 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.2769. Min Range: -11.2769
Max Act: 10.7144. Min Act: -0.1699
Data Index: 5985215 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.2769. Min Range: -11.2769
Max Act: 10.7144. Min Act: -0.1700
Data Index: 1793003 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.2769. Min Range: -11.2769
Max Act: 10.7144. Min Act: -0.1700
Data Index: 4719342 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.2769. Min Range: -11.2769
Max Act: 10.7144. Min Act: -0.1700
Data Index: 5455875 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.2769. Min Range: -11.2769
Max Act: 10.6519. Min Act: -0.1700
Data Index: 1377632 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.2769. Min Range: -11.2769
Max Act: 10.5894. Min Act: -0.1700
Data Index: 912396 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #19