Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3361 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5457. Min Range: -3.5457
Max Act: 3.5457. Min Act: -0.1700
Data Index: 1596990 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5457. Min Range: -3.5457
Max Act: 3.3419. Min Act: -0.1700
Data Index: 4221747 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5457. Min Range: -3.5457
Max Act: 3.3576. Min Act: -0.1700
Data Index: 243854 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5457. Min Range: -3.5457
Max Act: 3.2948. Min Act: -0.1700
Data Index: 3693085 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5457. Min Range: -3.5457
Max Act: 3.2634. Min Act: -0.1700
Data Index: 5516558 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5457. Min Range: -3.5457
Max Act: 3.2477. Min Act: -0.1700
Data Index: 1590422 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5457. Min Range: -3.5457
Max Act: 3.2006. Min Act: -0.1700
Data Index: 155198 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5457. Min Range: -3.5457
Max Act: 3.1691. Min Act: -0.1700
Data Index: 536023 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5457. Min Range: -3.5457
Max Act: 3.1534. Min Act: -0.1700
Data Index: 499383 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5457. Min Range: -3.5457
Max Act: 3.1376. Min Act: -0.1700
Data Index: 6923967 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5457. Min Range: -3.5457
Max Act: 3.1061. Min Act: -0.1700
Data Index: 4846512 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5457. Min Range: -3.5457
Max Act: 3.1219. Min Act: -0.1700
Data Index: 1925580 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5457. Min Range: -3.5457
Max Act: 3.1061. Min Act: -0.1700
Data Index: 8089620 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5457. Min Range: -3.5457
Max Act: 3.1061. Min Act: -0.1700
Data Index: 7644713 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5457. Min Range: -3.5457
Max Act: 3.0904. Min Act: -0.1700
Data Index: 5824900 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5457. Min Range: -3.5457
Max Act: 3.0904. Min Act: -0.1700
Data Index: 4816290 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5457. Min Range: -3.5457
Max Act: 3.0904. Min Act: -0.1700
Data Index: 3331484 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5457. Min Range: -3.5457
Max Act: 3.0588. Min Act: -0.1700
Data Index: 3790208 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5457. Min Range: -3.5457
Max Act: 3.0588. Min Act: -0.1700
Data Index: 789693 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5457. Min Range: -3.5457
Max Act: 3.0746. Min Act: -0.1700
Data Index: 6449649 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19