Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1676 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9451. Min Range: -5.9451
Max Act: 5.9451. Min Act: -0.1700
Data Index: 5057149 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9451. Min Range: -5.9451
Max Act: 5.8201. Min Act: -0.1700
Data Index: 337840 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9451. Min Range: -5.9451
Max Act: 5.7889. Min Act: -0.1700
Data Index: 4017704 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9451. Min Range: -5.9451
Max Act: 5.7264. Min Act: -0.1700
Data Index: 998666 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9451. Min Range: -5.9451
Max Act: 5.6951. Min Act: -0.1700
Data Index: 2305627 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9451. Min Range: -5.9451
Max Act: 5.6639. Min Act: -0.1700
Data Index: 6949460 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9451. Min Range: -5.9451
Max Act: 5.6639. Min Act: -0.1700
Data Index: 3270093 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9451. Min Range: -5.9451
Max Act: 5.6326. Min Act: -0.1700
Data Index: 3790942 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9451. Min Range: -5.9451
Max Act: 5.6326. Min Act: -0.1700
Data Index: 4129430 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9451. Min Range: -5.9451
Max Act: 5.6326. Min Act: -0.1700
Data Index: 2041068 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9451. Min Range: -5.9451
Max Act: 5.5701. Min Act: -0.1700
Data Index: 1152358 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9451. Min Range: -5.9451
Max Act: 5.5701. Min Act: -0.1700
Data Index: 7742819 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9451. Min Range: -5.9451
Max Act: 5.5389. Min Act: -0.1700
Data Index: 3295913 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9451. Min Range: -5.9451
Max Act: 5.4764. Min Act: -0.1700
Data Index: 8091656 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9451. Min Range: -5.9451
Max Act: 5.4451. Min Act: -0.1700
Data Index: 3697466 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9451. Min Range: -5.9451
Max Act: 5.4451. Min Act: -0.1700
Data Index: 6447167 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9451. Min Range: -5.9451
Max Act: 5.4451. Min Act: -0.1700
Data Index: 5600854 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9451. Min Range: -5.9451
Max Act: 5.4451. Min Act: -0.1700
Data Index: 372305 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9451. Min Range: -5.9451
Max Act: 5.4451. Min Act: -0.1700
Data Index: 4877428 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9451. Min Range: -5.9451
Max Act: 5.4139. Min Act: -0.1700
Data Index: 636304 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #19