Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3000 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4035. Min Range: -4.4035
Max Act: 4.4035. Min Act: -0.1700
Data Index: 4322688 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4035. Min Range: -4.4035
Max Act: 4.3410. Min Act: -0.1700
Data Index: 5598661 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4035. Min Range: -4.4035
Max Act: 4.2160. Min Act: -0.1700
Data Index: 7841833 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4035. Min Range: -4.4035
Max Act: 4.1847. Min Act: -0.1700
Data Index: 3896340 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4035. Min Range: -4.4035
Max Act: 4.1222. Min Act: -0.1700
Data Index: 5598660 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4035. Min Range: -4.4035
Max Act: 4.1222. Min Act: -0.1700
Data Index: 2920754 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4035. Min Range: -4.4035
Max Act: 4.1222. Min Act: -0.1700
Data Index: 4100862 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4035. Min Range: -4.4035
Max Act: 4.0597. Min Act: -0.1700
Data Index: 517504 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4035. Min Range: -4.4035
Max Act: 3.9347. Min Act: -0.1700
Data Index: 1704547 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4035. Min Range: -4.4035
Max Act: 3.9347. Min Act: -0.1700
Data Index: 4052570 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4035. Min Range: -4.4035
Max Act: 3.9034. Min Act: -0.1700
Data Index: 3329048 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4035. Min Range: -4.4035
Max Act: 3.9347. Min Act: -0.1700
Data Index: 2572800 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4035. Min Range: -4.4035
Max Act: 3.8721. Min Act: -0.1700
Data Index: 5885387 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4035. Min Range: -4.4035
Max Act: 3.8721. Min Act: -0.1700
Data Index: 7129926 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4035. Min Range: -4.4035
Max Act: 3.8409. Min Act: -0.1700
Data Index: 5868821 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4035. Min Range: -4.4035
Max Act: 3.8409. Min Act: -0.1700
Data Index: 2034090 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4035. Min Range: -4.4035
Max Act: 3.8409. Min Act: -0.1700
Data Index: 64390 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4035. Min Range: -4.4035
Max Act: 3.8409. Min Act: -0.1700
Data Index: 5695951 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4035. Min Range: -4.4035
Max Act: 3.8096. Min Act: -0.1700
Data Index: 4810464 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4035. Min Range: -4.4035
Max Act: 3.8096. Min Act: -0.1700
Data Index: 725618 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #19