Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2584 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9448. Min Range: -8.9448
Max Act: 8.9448. Min Act: -0.1700
Data Index: 5502242 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9448. Min Range: -8.9448
Max Act: 8.6948. Min Act: -0.1700
Data Index: 398690 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9448. Min Range: -8.9448
Max Act: 8.6323. Min Act: -0.1700
Data Index: 5339044 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9448. Min Range: -8.9448
Max Act: 8.6323. Min Act: -0.1700
Data Index: 4999759 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9448. Min Range: -8.9448
Max Act: 8.3198. Min Act: -0.1700
Data Index: 4906403 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9448. Min Range: -8.9448
Max Act: 8.3198. Min Act: -0.1700
Data Index: 6519894 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9448. Min Range: -8.9448
Max Act: 8.2573. Min Act: -0.1700
Data Index: 7276219 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9448. Min Range: -8.9448
Max Act: 8.2573. Min Act: -0.1700
Data Index: 1365607 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9448. Min Range: -8.9448
Max Act: 8.2573. Min Act: -0.1700
Data Index: 6882827 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9448. Min Range: -8.9448
Max Act: 8.1948. Min Act: -0.1700
Data Index: 4978817 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9448. Min Range: -8.9448
Max Act: 8.1323. Min Act: -0.1700
Data Index: 5498546 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9448. Min Range: -8.9448
Max Act: 8.1323. Min Act: -0.1700
Data Index: 8812636 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9448. Min Range: -8.9448
Max Act: 8.1323. Min Act: -0.1700
Data Index: 6975565 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9448. Min Range: -8.9448
Max Act: 8.0698. Min Act: -0.1700
Data Index: 6418200 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9448. Min Range: -8.9448
Max Act: 8.0698. Min Act: -0.1700
Data Index: 2222474 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9448. Min Range: -8.9448
Max Act: 8.0698. Min Act: -0.1700
Data Index: 3701816 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9448. Min Range: -8.9448
Max Act: 8.0698. Min Act: -0.1700
Data Index: 7742566 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9448. Min Range: -8.9448
Max Act: 8.0698. Min Act: -0.1700
Data Index: 1100753 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9448. Min Range: -8.9448
Max Act: 8.0073. Min Act: -0.1700
Data Index: 1649075 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9448. Min Range: -8.9448
Max Act: 8.0073. Min Act: -0.1700
Data Index: 119253 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19