Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4309 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0325. Min Range: -6.0325
Max Act: 6.0325. Min Act: -0.1700
Data Index: 2527094 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0325. Min Range: -6.0325
Max Act: 5.9700. Min Act: -0.1700
Data Index: 454505 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0325. Min Range: -6.0325
Max Act: 5.8763. Min Act: -0.1700
Data Index: 3698771 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0325. Min Range: -6.0325
Max Act: 5.7200. Min Act: -0.1700
Data Index: 6555922 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0325. Min Range: -6.0325
Max Act: 5.6888. Min Act: -0.1700
Data Index: 8670971 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0325. Min Range: -6.0325
Max Act: 5.6888. Min Act: -0.1700
Data Index: 8648804 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0325. Min Range: -6.0325
Max Act: 5.6575. Min Act: -0.1700
Data Index: 8237623 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0325. Min Range: -6.0325
Max Act: 5.6263. Min Act: -0.1700
Data Index: 1028094 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0325. Min Range: -6.0325
Max Act: 5.6263. Min Act: -0.1700
Data Index: 2002662 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0325. Min Range: -6.0325
Max Act: 5.5950. Min Act: -0.1700
Data Index: 1671085 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0325. Min Range: -6.0325
Max Act: 5.5950. Min Act: -0.1700
Data Index: 8747470 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0325. Min Range: -6.0325
Max Act: 5.5950. Min Act: -0.1700
Data Index: 3994544 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0325. Min Range: -6.0325
Max Act: 5.5950. Min Act: -0.1700
Data Index: 5284830 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0325. Min Range: -6.0325
Max Act: 5.5950. Min Act: -0.1700
Data Index: 1318355 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0325. Min Range: -6.0325
Max Act: 5.5638. Min Act: -0.1700
Data Index: 7490570 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0325. Min Range: -6.0325
Max Act: 5.5638. Min Act: -0.1700
Data Index: 3554125 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0325. Min Range: -6.0325
Max Act: 5.5638. Min Act: -0.1700
Data Index: 6688312 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0325. Min Range: -6.0325
Max Act: 5.5638. Min Act: -0.1700
Data Index: 7396850 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0325. Min Range: -6.0325
Max Act: 5.5325. Min Act: -0.1700
Data Index: 1586083 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0325. Min Range: -6.0325
Max Act: 5.5325. Min Act: -0.1700
Data Index: 99186 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #19