Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3986 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8503. Min Range: -5.8503
Max Act: 5.8503. Min Act: -0.1700
Data Index: 3750256 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8503. Min Range: -5.8503
Max Act: 5.7253. Min Act: -0.1700
Data Index: 3750255 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8503. Min Range: -5.8503
Max Act: 5.7253. Min Act: -0.1700
Data Index: 7727258 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8503. Min Range: -5.8503
Max Act: 5.6628. Min Act: -0.1700
Data Index: 3484038 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8503. Min Range: -5.8503
Max Act: 5.6003. Min Act: -0.1700
Data Index: 209113 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8503. Min Range: -5.8503
Max Act: 5.6003. Min Act: -0.1700
Data Index: 1042506 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8503. Min Range: -5.8503
Max Act: 5.5378. Min Act: -0.1700
Data Index: 7620312 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8503. Min Range: -5.8503
Max Act: 5.5378. Min Act: -0.1700
Data Index: 231041 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8503. Min Range: -5.8503
Max Act: 5.5378. Min Act: -0.1700
Data Index: 1013704 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8503. Min Range: -5.8503
Max Act: 5.5066. Min Act: -0.1700
Data Index: 4276045 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8503. Min Range: -5.8503
Max Act: 5.4753. Min Act: -0.1700
Data Index: 6933736 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8503. Min Range: -5.8503
Max Act: 5.4441. Min Act: -0.1700
Data Index: 898352 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8503. Min Range: -5.8503
Max Act: 5.4441. Min Act: -0.1700
Data Index: 911680 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8503. Min Range: -5.8503
Max Act: 5.4128. Min Act: -0.1700
Data Index: 8683649 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8503. Min Range: -5.8503
Max Act: 5.4128. Min Act: -0.1700
Data Index: 6928888 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8503. Min Range: -5.8503
Max Act: 5.4128. Min Act: -0.1700
Data Index: 6976480 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8503. Min Range: -5.8503
Max Act: 5.4128. Min Act: -0.1700
Data Index: 1831282 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8503. Min Range: -5.8503
Max Act: 5.3816. Min Act: -0.1700
Data Index: 7159340 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8503. Min Range: -5.8503
Max Act: 5.3816. Min Act: -0.1700
Data Index: 8410937 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8503. Min Range: -5.8503
Max Act: 5.3503. Min Act: -0.1700
Data Index: 2823792 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #19