Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3501 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4105. Min Range: -3.4105
Max Act: 3.4105. Min Act: -0.1700
Data Index: 6737141 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4105. Min Range: -3.4105
Max Act: 3.3478. Min Act: -0.1700
Data Index: 982458 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4105. Min Range: -3.4105
Max Act: 3.3164. Min Act: -0.1700
Data Index: 5242236 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4105. Min Range: -3.4105
Max Act: 3.3164. Min Act: -0.1700
Data Index: 2215567 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4105. Min Range: -3.4105
Max Act: 3.3007. Min Act: -0.1700
Data Index: 712949 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4105. Min Range: -3.4105
Max Act: 3.2850. Min Act: -0.1700
Data Index: 5170953 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4105. Min Range: -3.4105
Max Act: 3.2536. Min Act: -0.1700
Data Index: 5224893 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4105. Min Range: -3.4105
Max Act: 3.2379. Min Act: -0.1700
Data Index: 865711 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4105. Min Range: -3.4105
Max Act: 3.2379. Min Act: -0.1700
Data Index: 4665217 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4105. Min Range: -3.4105
Max Act: 3.2379. Min Act: -0.1700
Data Index: 2737037 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4105. Min Range: -3.4105
Max Act: 3.2222. Min Act: -0.1700
Data Index: 598055 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4105. Min Range: -3.4105
Max Act: 3.2222. Min Act: -0.1700
Data Index: 5630746 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4105. Min Range: -3.4105
Max Act: 3.2222. Min Act: -0.1700
Data Index: 5677201 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4105. Min Range: -3.4105
Max Act: 3.2064. Min Act: -0.1700
Data Index: 20098 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4105. Min Range: -3.4105
Max Act: 3.1907. Min Act: -0.1700
Data Index: 3684847 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4105. Min Range: -3.4105
Max Act: 3.1907. Min Act: -0.1700
Data Index: 4576896 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4105. Min Range: -3.4105
Max Act: 3.2064. Min Act: -0.1700
Data Index: 7749107 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4105. Min Range: -3.4105
Max Act: 3.2064. Min Act: -0.1700
Data Index: 4732847 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4105. Min Range: -3.4105
Max Act: 3.1750. Min Act: -0.1700
Data Index: 4289902 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4105. Min Range: -3.4105
Max Act: 3.1750. Min Act: -0.1700
Data Index: 4352852 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #19