Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2027 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.8324. Min Range: -0.8324
Max Act: 0.8324. Min Act: -0.1628
Data Index: 5011569 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8324. Min Range: -0.8324
Max Act: 0.7904. Min Act: -0.1691
Data Index: 8279723 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8324. Min Range: -0.8324
Max Act: 0.7737. Min Act: -0.1659
Data Index: 188038 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8324. Min Range: -0.8324
Max Act: 0.6913. Min Act: -0.1700
Data Index: 3935322 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8324. Min Range: -0.8324
Max Act: 0.6751. Min Act: -0.1699
Data Index: 1550542 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8324. Min Range: -0.8324
Max Act: 0.6751. Min Act: -0.1490
Data Index: 3142450 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8324. Min Range: -0.8324
Max Act: 0.6670. Min Act: -0.1695
Data Index: 5966901 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8324. Min Range: -0.8324
Max Act: 0.6670. Min Act: -0.1698
Data Index: 1318818 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8324. Min Range: -0.8324
Max Act: 0.6589. Min Act: -0.1700
Data Index: 5966898 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8324. Min Range: -0.8324
Max Act: 0.6509. Min Act: -0.1700
Data Index: 2654948 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8324. Min Range: -0.8324
Max Act: 0.6670. Min Act: -0.1700
Data Index: 735598 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8324. Min Range: -0.8324
Max Act: 0.6509. Min Act: -0.1700
Data Index: 4672471 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8324. Min Range: -0.8324
Max Act: 0.6429. Min Act: -0.1699
Data Index: 8180617 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8324. Min Range: -0.8324
Max Act: 0.6429. Min Act: -0.1697
Data Index: 7407775 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8324. Min Range: -0.8324
Max Act: 0.6429. Min Act: -0.1700
Data Index: 7142624 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8324. Min Range: -0.8324
Max Act: 0.6349. Min Act: -0.1695
Data Index: 3230187 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8324. Min Range: -0.8324
Max Act: 0.6349. Min Act: -0.1586
Data Index: 5966885 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8324. Min Range: -0.8324
Max Act: 0.6269. Min Act: -0.1700
Data Index: 5966911 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8324. Min Range: -0.8324
Max Act: 0.6269. Min Act: -0.1698
Data Index: 2906225 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8324. Min Range: -0.8324
Max Act: 0.6190. Min Act: -0.1109
Data Index: 2039843 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #19