Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6379 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3340. Min Range: -5.3340
Max Act: 5.3340. Min Act: -0.1700
Data Index: 3771322 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3340. Min Range: -5.3340
Max Act: 5.2715. Min Act: -0.1700
Data Index: 2094888 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3340. Min Range: -5.3340
Max Act: 5.1465. Min Act: -0.1700
Data Index: 8589624 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3340. Min Range: -5.3340
Max Act: 5.0840. Min Act: -0.1700
Data Index: 8688442 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3340. Min Range: -5.3340
Max Act: 5.0528. Min Act: -0.1700
Data Index: 8791752 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3340. Min Range: -5.3340
Max Act: 5.0840. Min Act: -0.1700
Data Index: 367576 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3340. Min Range: -5.3340
Max Act: 5.0215. Min Act: -0.1700
Data Index: 3005385 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3340. Min Range: -5.3340
Max Act: 5.0215. Min Act: -0.1700
Data Index: 5178920 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3340. Min Range: -5.3340
Max Act: 5.0215. Min Act: -0.1700
Data Index: 3660627 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3340. Min Range: -5.3340
Max Act: 5.0215. Min Act: -0.1700
Data Index: 3619267 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3340. Min Range: -5.3340
Max Act: 4.9903. Min Act: -0.1700
Data Index: 1531614 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3340. Min Range: -5.3340
Max Act: 4.9903. Min Act: -0.1700
Data Index: 6117802 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3340. Min Range: -5.3340
Max Act: 4.9590. Min Act: -0.1700
Data Index: 4114395 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3340. Min Range: -5.3340
Max Act: 4.9590. Min Act: -0.1700
Data Index: 1831639 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3340. Min Range: -5.3340
Max Act: 4.9278. Min Act: -0.1700
Data Index: 5334781 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3340. Min Range: -5.3340
Max Act: 4.9278. Min Act: -0.1700
Data Index: 852902 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3340. Min Range: -5.3340
Max Act: 4.9278. Min Act: -0.1700
Data Index: 409276 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3340. Min Range: -5.3340
Max Act: 4.8965. Min Act: -0.1700
Data Index: 4232006 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3340. Min Range: -5.3340
Max Act: 4.8965. Min Act: -0.1700
Data Index: 1661513 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3340. Min Range: -5.3340
Max Act: 4.8653. Min Act: -0.1700
Data Index: 510688 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #19