Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4504 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7608. Min Range: -6.7608
Max Act: 6.7608. Min Act: -0.1700
Data Index: 8546917 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7608. Min Range: -6.7608
Max Act: 6.6983. Min Act: -0.1700
Data Index: 5013900 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7608. Min Range: -6.7608
Max Act: 6.6671. Min Act: -0.1700
Data Index: 7179500 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7608. Min Range: -6.7608
Max Act: 6.5421. Min Act: -0.1700
Data Index: 4937373 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7608. Min Range: -6.7608
Max Act: 6.5421. Min Act: -0.1700
Data Index: 2365354 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7608. Min Range: -6.7608
Max Act: 6.4483. Min Act: -0.1700
Data Index: 3608130 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7608. Min Range: -6.7608
Max Act: 6.4171. Min Act: -0.1700
Data Index: 6277812 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7608. Min Range: -6.7608
Max Act: 6.3233. Min Act: -0.1700
Data Index: 4036362 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7608. Min Range: -6.7608
Max Act: 6.3546. Min Act: -0.1700
Data Index: 4470609 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7608. Min Range: -6.7608
Max Act: 6.3233. Min Act: -0.1700
Data Index: 1316639 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7608. Min Range: -6.7608
Max Act: 6.3546. Min Act: -0.1700
Data Index: 5620443 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7608. Min Range: -6.7608
Max Act: 6.2921. Min Act: -0.1700
Data Index: 1597924 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7608. Min Range: -6.7608
Max Act: 6.2921. Min Act: -0.1700
Data Index: 2959403 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7608. Min Range: -6.7608
Max Act: 6.2608. Min Act: -0.1700
Data Index: 7824345 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7608. Min Range: -6.7608
Max Act: 6.2608. Min Act: -0.1700
Data Index: 6489058 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7608. Min Range: -6.7608
Max Act: 6.2608. Min Act: -0.1700
Data Index: 4811557 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7608. Min Range: -6.7608
Max Act: 6.2296. Min Act: -0.1700
Data Index: 4078796 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7608. Min Range: -6.7608
Max Act: 6.1983. Min Act: -0.1700
Data Index: 8457447 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7608. Min Range: -6.7608
Max Act: 6.1983. Min Act: -0.1700
Data Index: 8542247 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7608. Min Range: -6.7608
Max Act: 6.1671. Min Act: -0.1700
Data Index: 935877 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19