Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3853 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2685. Min Range: -5.2685
Max Act: 5.2685. Min Act: -0.1700
Data Index: 2325896 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2685. Min Range: -5.2685
Max Act: 5.2685. Min Act: -0.1700
Data Index: 7663118 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2685. Min Range: -5.2685
Max Act: 5.2685. Min Act: -0.1700
Data Index: 5198363 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2685. Min Range: -5.2685
Max Act: 5.2373. Min Act: -0.1699
Data Index: 6054913 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2685. Min Range: -5.2685
Max Act: 5.2373. Min Act: -0.1700
Data Index: 3721641 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2685. Min Range: -5.2685
Max Act: 5.2373. Min Act: -0.1699
Data Index: 4147385 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2685. Min Range: -5.2685
Max Act: 5.1748. Min Act: -0.1699
Data Index: 5267652 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2685. Min Range: -5.2685
Max Act: 5.2060. Min Act: -0.1700
Data Index: 5252152 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2685. Min Range: -5.2685
Max Act: 5.2060. Min Act: -0.1699
Data Index: 5180207 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2685. Min Range: -5.2685
Max Act: 5.2060. Min Act: -0.1700
Data Index: 4943683 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2685. Min Range: -5.2685
Max Act: 5.2060. Min Act: -0.1700
Data Index: 6885831 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2685. Min Range: -5.2685
Max Act: 5.2060. Min Act: -0.1700
Data Index: 6077984 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2685. Min Range: -5.2685
Max Act: 5.2060. Min Act: -0.1700
Data Index: 3898258 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2685. Min Range: -5.2685
Max Act: 5.1748. Min Act: -0.1700
Data Index: 6059108 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2685. Min Range: -5.2685
Max Act: 5.1748. Min Act: -0.1699
Data Index: 3638479 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2685. Min Range: -5.2685
Max Act: 5.2060. Min Act: -0.1699
Data Index: 2865004 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2685. Min Range: -5.2685
Max Act: 5.1748. Min Act: -0.1700
Data Index: 3138489 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2685. Min Range: -5.2685
Max Act: 5.1748. Min Act: -0.1699
Data Index: 176940 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2685. Min Range: -5.2685
Max Act: 5.1748. Min Act: -0.1700
Data Index: 314306 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2685. Min Range: -5.2685
Max Act: 5.1748. Min Act: -0.1700
Data Index: 1625812 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19