Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3598 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.2552. Min Range: -1.2552
Max Act: 1.2552. Min Act: -0.1648
Data Index: 344909 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2552. Min Range: -1.2552
Max Act: 1.2200. Min Act: -0.1699
Data Index: 2285596 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2552. Min Range: -1.2552
Max Act: 1.2023. Min Act: -0.1690
Data Index: 8691047 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2552. Min Range: -1.2552
Max Act: 1.1496. Min Act: -0.1698
Data Index: 6726648 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2552. Min Range: -1.2552
Max Act: 1.1496. Min Act: -0.1700
Data Index: 4216345 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2552. Min Range: -1.2552
Max Act: 1.1320. Min Act: -0.1700
Data Index: 5477741 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2552. Min Range: -1.2552
Max Act: 1.1320. Min Act: -0.1700
Data Index: 5571760 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2552. Min Range: -1.2552
Max Act: 1.1145. Min Act: -0.1689
Data Index: 4269160 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2552. Min Range: -1.2552
Max Act: 1.0794. Min Act: -0.1696
Data Index: 5505855 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2552. Min Range: -1.2552
Max Act: 1.0794. Min Act: -0.1678
Data Index: 5288700 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2552. Min Range: -1.2552
Max Act: 1.0707. Min Act: -0.1696
Data Index: 3407906 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2552. Min Range: -1.2552
Max Act: 1.0532. Min Act: -0.1659
Data Index: 2874038 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2552. Min Range: -1.2552
Max Act: 1.0271. Min Act: -0.1693
Data Index: 8093169 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2552. Min Range: -1.2552
Max Act: 1.0271. Min Act: -0.1700
Data Index: 6772467 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2552. Min Range: -1.2552
Max Act: 1.0358. Min Act: -0.1700
Data Index: 5855115 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2552. Min Range: -1.2552
Max Act: 1.0445. Min Act: -0.1700
Data Index: 7423475 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2552. Min Range: -1.2552
Max Act: 1.0184. Min Act: -0.1694
Data Index: 6617786 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2552. Min Range: -1.2552
Max Act: 1.0184. Min Act: -0.1700
Data Index: 7423476 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2552. Min Range: -1.2552
Max Act: 1.0097. Min Act: -0.1700
Data Index: 3057209 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2552. Min Range: -1.2552
Max Act: 1.0097. Min Act: -0.1699
Data Index: 4921108 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #19