Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3905 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.1607. Min Range: -2.1607
Max Act: 2.1607. Min Act: -0.1699
Data Index: 7352749 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1607. Min Range: -2.1607
Max Act: 2.1607. Min Act: -0.1687
Data Index: 5943116 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1607. Min Range: -2.1607
Max Act: 2.0435. Min Act: -0.1679
Data Index: 6339379 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1607. Min Range: -2.1607
Max Act: 2.0435. Min Act: -0.1700
Data Index: 6905782 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1607. Min Range: -2.1607
Max Act: 2.0267. Min Act: -0.1700
Data Index: 2513140 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1607. Min Range: -2.1607
Max Act: 2.0267. Min Act: -0.1687
Data Index: 2921763 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1607. Min Range: -2.1607
Max Act: 2.0098. Min Act: -0.1695
Data Index: 469381 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1607. Min Range: -2.1607
Max Act: 1.9929. Min Act: -0.1700
Data Index: 2247293 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1607. Min Range: -2.1607
Max Act: 1.9929. Min Act: -0.1700
Data Index: 3206033 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1607. Min Range: -2.1607
Max Act: 1.9760. Min Act: -0.1699
Data Index: 8814767 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1607. Min Range: -2.1607
Max Act: 1.9760. Min Act: -0.1669
Data Index: 3122703 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1607. Min Range: -2.1607
Max Act: 1.9590. Min Act: -0.1699
Data Index: 8133889 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1607. Min Range: -2.1607
Max Act: 1.9590. Min Act: -0.1652
Data Index: 1619650 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1607. Min Range: -2.1607
Max Act: 1.9590. Min Act: -0.1700
Data Index: 5496257 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1607. Min Range: -2.1607
Max Act: 1.9590. Min Act: -0.1700
Data Index: 3203250 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1607. Min Range: -2.1607
Max Act: 1.9590. Min Act: -0.1699
Data Index: 8410479 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1607. Min Range: -2.1607
Max Act: 1.9590. Min Act: -0.1641
Data Index: 3381823 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1607. Min Range: -2.1607
Max Act: 1.9420. Min Act: -0.1681
Data Index: 6328529 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1607. Min Range: -2.1607
Max Act: 1.9250. Min Act: -0.1697
Data Index: 1645519 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1607. Min Range: -2.1607
Max Act: 1.9420. Min Act: -0.1700
Data Index: 8247226 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #19