Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3754 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6774. Min Range: -6.6774
Max Act: 6.6774. Min Act: -0.1700
Data Index: 2174267 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6774. Min Range: -6.6774
Max Act: 6.5837. Min Act: -0.1700
Data Index: 7125258 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6774. Min Range: -6.6774
Max Act: 6.5837. Min Act: -0.0950
Data Index: 5383479 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6774. Min Range: -6.6774
Max Act: 6.5837. Min Act: -0.1700
Data Index: 3892036 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6774. Min Range: -6.6774
Max Act: 6.5212. Min Act: -0.1700
Data Index: 4621590 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6774. Min Range: -6.6774
Max Act: 6.5212. Min Act: -0.1700
Data Index: 8391561 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6774. Min Range: -6.6774
Max Act: 6.5212. Min Act: -0.1700
Data Index: 6628070 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6774. Min Range: -6.6774
Max Act: 6.4274. Min Act: -0.1657
Data Index: 4453166 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6774. Min Range: -6.6774
Max Act: 6.3962. Min Act: -0.1700
Data Index: 5257476 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6774. Min Range: -6.6774
Max Act: 6.4274. Min Act: -0.1700
Data Index: 3453121 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6774. Min Range: -6.6774
Max Act: 6.3962. Min Act: -0.1699
Data Index: 4016849 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6774. Min Range: -6.6774
Max Act: 6.3962. Min Act: -0.1698
Data Index: 4016847 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6774. Min Range: -6.6774
Max Act: 6.3649. Min Act: -0.1700
Data Index: 1552953 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6774. Min Range: -6.6774
Max Act: 6.3962. Min Act: -0.1700
Data Index: 4016846 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6774. Min Range: -6.6774
Max Act: 6.3962. Min Act: -0.1700
Data Index: 2010050 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6774. Min Range: -6.6774
Max Act: 6.3962. Min Act: -0.1694
Data Index: 3055441 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6774. Min Range: -6.6774
Max Act: 6.3649. Min Act: -0.1700
Data Index: 2090301 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6774. Min Range: -6.6774
Max Act: 6.3649. Min Act: -0.1700
Data Index: 2961588 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6774. Min Range: -6.6774
Max Act: 6.3337. Min Act: -0.0950
Data Index: 5383480 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6774. Min Range: -6.6774
Max Act: 6.3337. Min Act: -0.1700
Data Index: 5678084 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19