Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5107 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6340. Min Range: -6.6340
Max Act: 6.6340. Min Act: -0.1700
Data Index: 5764703 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6340. Min Range: -6.6340
Max Act: 6.6027. Min Act: -0.1700
Data Index: 6179242 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6340. Min Range: -6.6340
Max Act: 6.4465. Min Act: -0.1700
Data Index: 1279227 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6340. Min Range: -6.6340
Max Act: 6.4465. Min Act: -0.1700
Data Index: 3462038 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6340. Min Range: -6.6340
Max Act: 6.4152. Min Act: -0.1700
Data Index: 2127796 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6340. Min Range: -6.6340
Max Act: 6.3840. Min Act: -0.1700
Data Index: 4819550 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6340. Min Range: -6.6340
Max Act: 6.3840. Min Act: -0.1700
Data Index: 667019 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6340. Min Range: -6.6340
Max Act: 6.3527. Min Act: -0.1700
Data Index: 6616993 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6340. Min Range: -6.6340
Max Act: 6.3527. Min Act: -0.1700
Data Index: 716837 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6340. Min Range: -6.6340
Max Act: 6.3527. Min Act: -0.1700
Data Index: 377326 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6340. Min Range: -6.6340
Max Act: 6.3215. Min Act: -0.1700
Data Index: 6052678 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6340. Min Range: -6.6340
Max Act: 6.3215. Min Act: -0.1700
Data Index: 4124264 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6340. Min Range: -6.6340
Max Act: 6.2902. Min Act: -0.1700
Data Index: 6978992 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6340. Min Range: -6.6340
Max Act: 6.3215. Min Act: -0.1700
Data Index: 482541 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6340. Min Range: -6.6340
Max Act: 6.2902. Min Act: -0.1700
Data Index: 346708 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6340. Min Range: -6.6340
Max Act: 6.3215. Min Act: -0.1700
Data Index: 4440672 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6340. Min Range: -6.6340
Max Act: 6.2902. Min Act: -0.1700
Data Index: 8366040 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6340. Min Range: -6.6340
Max Act: 6.2902. Min Act: -0.1700
Data Index: 1256401 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6340. Min Range: -6.6340
Max Act: 6.2590. Min Act: -0.1700
Data Index: 2884731 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6340. Min Range: -6.6340
Max Act: 6.2590. Min Act: -0.1700
Data Index: 2888998 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #19