Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3411 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.6896. Min Range: -1.6896
Max Act: 1.6896. Min Act: -0.1643
Data Index: 8460817 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6896. Min Range: -1.6896
Max Act: 1.4975. Min Act: -0.1634
Data Index: 613406 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6896. Min Range: -1.6896
Max Act: 1.4271. Min Act: -0.1628
Data Index: 6562498 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6896. Min Range: -1.6896
Max Act: 1.4095. Min Act: -0.1700
Data Index: 5438954 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6896. Min Range: -1.6896
Max Act: 1.3390. Min Act: -0.1682
Data Index: 6562500 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6896. Min Range: -1.6896
Max Act: 1.3390. Min Act: -0.1673
Data Index: 2894096 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6896. Min Range: -1.6896
Max Act: 1.3214. Min Act: -0.1646
Data Index: 262828 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6896. Min Range: -1.6896
Max Act: 1.3214. Min Act: -0.1700
Data Index: 8742472 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6896. Min Range: -1.6896
Max Act: 1.3037. Min Act: -0.1700
Data Index: 6285984 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6896. Min Range: -1.6896
Max Act: 1.2861. Min Act: -0.1700
Data Index: 4220221 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6896. Min Range: -1.6896
Max Act: 1.2861. Min Act: -0.1497
Data Index: 3339270 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6896. Min Range: -1.6896
Max Act: 1.2861. Min Act: -0.1667
Data Index: 6720122 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6896. Min Range: -1.6896
Max Act: 1.2684. Min Act: -0.1603
Data Index: 4975408 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6896. Min Range: -1.6896
Max Act: 1.2684. Min Act: -0.1677
Data Index: 3128977 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6896. Min Range: -1.6896
Max Act: 1.2684. Min Act: -0.1684
Data Index: 6562505 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6896. Min Range: -1.6896
Max Act: 1.2684. Min Act: -0.1699
Data Index: 4852908 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6896. Min Range: -1.6896
Max Act: 1.2508. Min Act: -0.1700
Data Index: 3170103 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6896. Min Range: -1.6896
Max Act: 1.2332. Min Act: -0.1446
Data Index: 304205 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6896. Min Range: -1.6896
Max Act: 1.2332. Min Act: -0.1696
Data Index: 1268816 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6896. Min Range: -1.6896
Max Act: 1.2332. Min Act: -0.1685
Data Index: 6482591 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19