Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5992 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4526. Min Range: -6.4526
Max Act: 6.4526. Min Act: -0.1700
Data Index: 139904 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4526. Min Range: -6.4526
Max Act: 6.3588. Min Act: -0.1700
Data Index: 5375959 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4526. Min Range: -6.4526
Max Act: 6.2963. Min Act: -0.1700
Data Index: 7631114 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4526. Min Range: -6.4526
Max Act: 6.2651. Min Act: -0.1700
Data Index: 53195 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4526. Min Range: -6.4526
Max Act: 6.2338. Min Act: -0.1700
Data Index: 7948582 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4526. Min Range: -6.4526
Max Act: 6.2338. Min Act: -0.1700
Data Index: 1041908 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4526. Min Range: -6.4526
Max Act: 6.2338. Min Act: -0.1700
Data Index: 2519784 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4526. Min Range: -6.4526
Max Act: 6.1713. Min Act: -0.1700
Data Index: 3746470 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4526. Min Range: -6.4526
Max Act: 6.1401. Min Act: -0.1700
Data Index: 6895410 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4526. Min Range: -6.4526
Max Act: 6.1088. Min Act: -0.1700
Data Index: 2779373 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4526. Min Range: -6.4526
Max Act: 6.0463. Min Act: -0.1700
Data Index: 8343721 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4526. Min Range: -6.4526
Max Act: 6.0463. Min Act: -0.1700
Data Index: 640573 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4526. Min Range: -6.4526
Max Act: 6.0151. Min Act: -0.1700
Data Index: 703082 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4526. Min Range: -6.4526
Max Act: 6.0151. Min Act: -0.1700
Data Index: 8645440 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4526. Min Range: -6.4526
Max Act: 6.0151. Min Act: -0.1700
Data Index: 625823 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4526. Min Range: -6.4526
Max Act: 5.9838. Min Act: -0.1700
Data Index: 4733045 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4526. Min Range: -6.4526
Max Act: 6.0151. Min Act: -0.1700
Data Index: 1771019 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4526. Min Range: -6.4526
Max Act: 5.9838. Min Act: -0.1700
Data Index: 8056552 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4526. Min Range: -6.4526
Max Act: 5.9526. Min Act: -0.1700
Data Index: 2003401 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4526. Min Range: -6.4526
Max Act: 5.9526. Min Act: -0.1700
Data Index: 3222296 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19