Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3978 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3912. Min Range: -4.3912
Max Act: 4.3912. Min Act: -0.1700
Data Index: 7085788 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3912. Min Range: -4.3912
Max Act: 4.3600. Min Act: -0.1700
Data Index: 4360143 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3912. Min Range: -4.3912
Max Act: 4.2975. Min Act: -0.1700
Data Index: 4360134 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3912. Min Range: -4.3912
Max Act: 4.2662. Min Act: -0.1700
Data Index: 3074096 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3912. Min Range: -4.3912
Max Act: 4.2350. Min Act: -0.1700
Data Index: 2819424 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3912. Min Range: -4.3912
Max Act: 4.2037. Min Act: -0.1700
Data Index: 7388716 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3912. Min Range: -4.3912
Max Act: 4.1725. Min Act: -0.1700
Data Index: 5188470 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3912. Min Range: -4.3912
Max Act: 4.1412. Min Act: -0.1700
Data Index: 7376545 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3912. Min Range: -4.3912
Max Act: 4.1412. Min Act: -0.1700
Data Index: 3250304 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3912. Min Range: -4.3912
Max Act: 4.1412. Min Act: -0.1700
Data Index: 4105076 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3912. Min Range: -4.3912
Max Act: 4.1100. Min Act: -0.1700
Data Index: 3471537 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3912. Min Range: -4.3912
Max Act: 4.1100. Min Act: -0.1700
Data Index: 6900148 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3912. Min Range: -4.3912
Max Act: 4.1100. Min Act: -0.1700
Data Index: 1153032 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3912. Min Range: -4.3912
Max Act: 4.0787. Min Act: -0.1700
Data Index: 401751 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3912. Min Range: -4.3912
Max Act: 4.0787. Min Act: -0.1700
Data Index: 3994569 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3912. Min Range: -4.3912
Max Act: 4.0787. Min Act: -0.1700
Data Index: 2521706 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3912. Min Range: -4.3912
Max Act: 4.0474. Min Act: -0.1700
Data Index: 118718 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3912. Min Range: -4.3912
Max Act: 4.0787. Min Act: -0.1700
Data Index: 1791807 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3912. Min Range: -4.3912
Max Act: 4.0787. Min Act: -0.1700
Data Index: 2066888 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3912. Min Range: -4.3912
Max Act: 4.0787. Min Act: -0.1700
Data Index: 1734106 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19