Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5161 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.5662. Min Range: -12.5662
Max Act: 12.5662. Min Act: -0.1700
Data Index: 8733544 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.5662. Min Range: -12.5662
Max Act: 12.4412. Min Act: -0.1699
Data Index: 6782076 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.5662. Min Range: -12.5662
Max Act: 12.1912. Min Act: -0.1700
Data Index: 8450003 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.5662. Min Range: -12.5662
Max Act: 12.1287. Min Act: -0.1700
Data Index: 7786880 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.5662. Min Range: -12.5662
Max Act: 12.0662. Min Act: -0.1700
Data Index: 7732697 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.5662. Min Range: -12.5662
Max Act: 12.1287. Min Act: -0.1700
Data Index: 4847984 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.5662. Min Range: -12.5662
Max Act: 12.0662. Min Act: -0.1698
Data Index: 4341862 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.5662. Min Range: -12.5662
Max Act: 11.9412. Min Act: -0.1700
Data Index: 2060744 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.5662. Min Range: -12.5662
Max Act: 12.0037. Min Act: -0.1700
Data Index: 4738759 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.5662. Min Range: -12.5662
Max Act: 12.0037. Min Act: -0.1700
Data Index: 3317350 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.5662. Min Range: -12.5662
Max Act: 12.0037. Min Act: -0.1697
Data Index: 662788 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.5662. Min Range: -12.5662
Max Act: 11.9412. Min Act: -0.1700
Data Index: 7777342 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.5662. Min Range: -12.5662
Max Act: 12.0037. Min Act: -0.1698
Data Index: 1086702 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.5662. Min Range: -12.5662
Max Act: 11.9412. Min Act: -0.1700
Data Index: 4300739 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.5662. Min Range: -12.5662
Max Act: 11.9412. Min Act: -0.1695
Data Index: 6060008 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.5662. Min Range: -12.5662
Max Act: 11.8787. Min Act: -0.1691
Data Index: 2844755 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.5662. Min Range: -12.5662
Max Act: 11.8787. Min Act: -0.1700
Data Index: 1912078 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.5662. Min Range: -12.5662
Max Act: 11.8787. Min Act: -0.1699
Data Index: 6879648 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.5662. Min Range: -12.5662
Max Act: 11.8787. Min Act: -0.1700
Data Index: 7224299 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.5662. Min Range: -12.5662
Max Act: 11.8787. Min Act: -0.1700
Data Index: 5561767 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19