Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3091 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.0412. Min Range: -2.0412
Max Act: 2.0412. Min Act: -0.1700
Data Index: 8679458 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0412. Min Range: -2.0412
Max Act: 2.0328. Min Act: -0.1700
Data Index: 7132142 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0412. Min Range: -2.0412
Max Act: 2.0159. Min Act: -0.1700
Data Index: 8475775 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0412. Min Range: -2.0412
Max Act: 2.0075. Min Act: -0.1694
Data Index: 5859560 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0412. Min Range: -2.0412
Max Act: 2.0075. Min Act: -0.1700
Data Index: 6642357 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0412. Min Range: -2.0412
Max Act: 1.9990. Min Act: -0.1700
Data Index: 6207700 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0412. Min Range: -2.0412
Max Act: 1.9906. Min Act: -0.1699
Data Index: 8365644 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0412. Min Range: -2.0412
Max Act: 1.9821. Min Act: -0.1700
Data Index: 7754644 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0412. Min Range: -2.0412
Max Act: 1.9821. Min Act: -0.1700
Data Index: 884202 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0412. Min Range: -2.0412
Max Act: 1.9736. Min Act: -0.1700
Data Index: 5455650 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0412. Min Range: -2.0412
Max Act: 1.9736. Min Act: -0.1700
Data Index: 6791552 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0412. Min Range: -2.0412
Max Act: 1.9736. Min Act: -0.1700
Data Index: 6570161 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0412. Min Range: -2.0412
Max Act: 1.9652. Min Act: -0.1700
Data Index: 7822145 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0412. Min Range: -2.0412
Max Act: 1.9652. Min Act: -0.1698
Data Index: 534002 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0412. Min Range: -2.0412
Max Act: 1.9567. Min Act: -0.1700
Data Index: 8325960 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0412. Min Range: -2.0412
Max Act: 1.9652. Min Act: -0.1700
Data Index: 7324012 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0412. Min Range: -2.0412
Max Act: 1.9567. Min Act: -0.1700
Data Index: 3885849 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0412. Min Range: -2.0412
Max Act: 1.9482. Min Act: -0.1700
Data Index: 8050953 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0412. Min Range: -2.0412
Max Act: 1.9397. Min Act: -0.1697
Data Index: 6094069 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0412. Min Range: -2.0412
Max Act: 1.9482. Min Act: -0.1695
Data Index: 6592810 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #19