Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3673 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2490. Min Range: -5.2490
Max Act: 5.2490. Min Act: -0.1700
Data Index: 4917122 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2490. Min Range: -5.2490
Max Act: 5.1553. Min Act: -0.1700
Data Index: 1144881 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2490. Min Range: -5.2490
Max Act: 5.0928. Min Act: -0.1700
Data Index: 4304712 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2490. Min Range: -5.2490
Max Act: 5.0615. Min Act: -0.1700
Data Index: 7851627 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2490. Min Range: -5.2490
Max Act: 5.0615. Min Act: -0.1700
Data Index: 2376507 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2490. Min Range: -5.2490
Max Act: 4.9990. Min Act: -0.1700
Data Index: 7531318 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2490. Min Range: -5.2490
Max Act: 4.9678. Min Act: -0.1700
Data Index: 8052202 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2490. Min Range: -5.2490
Max Act: 4.9678. Min Act: -0.1700
Data Index: 5953659 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2490. Min Range: -5.2490
Max Act: 4.9678. Min Act: -0.1700
Data Index: 7523071 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2490. Min Range: -5.2490
Max Act: 4.9678. Min Act: -0.1700
Data Index: 3982500 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2490. Min Range: -5.2490
Max Act: 4.9678. Min Act: -0.1700
Data Index: 6409468 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2490. Min Range: -5.2490
Max Act: 4.9365. Min Act: -0.1700
Data Index: 5547705 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2490. Min Range: -5.2490
Max Act: 4.9365. Min Act: -0.1700
Data Index: 3465623 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2490. Min Range: -5.2490
Max Act: 4.9365. Min Act: -0.1700
Data Index: 3708381 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2490. Min Range: -5.2490
Max Act: 4.8740. Min Act: -0.1700
Data Index: 712685 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2490. Min Range: -5.2490
Max Act: 4.9365. Min Act: -0.1700
Data Index: 8050417 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2490. Min Range: -5.2490
Max Act: 4.9053. Min Act: -0.1700
Data Index: 7865758 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2490. Min Range: -5.2490
Max Act: 4.8740. Min Act: -0.1700
Data Index: 4415611 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2490. Min Range: -5.2490
Max Act: 4.8740. Min Act: -0.1700
Data Index: 3975529 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2490. Min Range: -5.2490
Max Act: 4.8740. Min Act: -0.1700
Data Index: 6184331 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #19