Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4869 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.4596. Min Range: -11.4596
Max Act: 11.4596. Min Act: -0.1700
Data Index: 5335639 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.4596. Min Range: -11.4596
Max Act: 11.0221. Min Act: -0.1700
Data Index: 4971664 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.4596. Min Range: -11.4596
Max Act: 10.8346. Min Act: -0.1700
Data Index: 2254157 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.4596. Min Range: -11.4596
Max Act: 10.7096. Min Act: -0.1700
Data Index: 5131855 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.4596. Min Range: -11.4596
Max Act: 10.6471. Min Act: -0.1700
Data Index: 395130 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.4596. Min Range: -11.4596
Max Act: 10.5846. Min Act: -0.1700
Data Index: 6421981 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.4596. Min Range: -11.4596
Max Act: 10.5846. Min Act: -0.1700
Data Index: 907736 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.4596. Min Range: -11.4596
Max Act: 10.5221. Min Act: -0.1700
Data Index: 2760281 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.4596. Min Range: -11.4596
Max Act: 10.5221. Min Act: -0.1700
Data Index: 4480360 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.4596. Min Range: -11.4596
Max Act: 10.4596. Min Act: -0.1700
Data Index: 2633561 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.4596. Min Range: -11.4596
Max Act: 10.3971. Min Act: -0.1700
Data Index: 863003 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.4596. Min Range: -11.4596
Max Act: 10.3971. Min Act: -0.1700
Data Index: 6925403 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.4596. Min Range: -11.4596
Max Act: 10.3346. Min Act: -0.1700
Data Index: 6923623 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.4596. Min Range: -11.4596
Max Act: 10.3346. Min Act: -0.1700
Data Index: 5833348 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.4596. Min Range: -11.4596
Max Act: 10.3346. Min Act: -0.1700
Data Index: 4012854 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.4596. Min Range: -11.4596
Max Act: 10.3971. Min Act: -0.1700
Data Index: 7115358 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.4596. Min Range: -11.4596
Max Act: 10.2721. Min Act: -0.1700
Data Index: 885908 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.4596. Min Range: -11.4596
Max Act: 10.2721. Min Act: -0.1700
Data Index: 6935060 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.4596. Min Range: -11.4596
Max Act: 10.2721. Min Act: -0.1700
Data Index: 6765595 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.4596. Min Range: -11.4596
Max Act: 10.2721. Min Act: -0.1700
Data Index: 4391044 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19