Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3734 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8527. Min Range: -7.8527
Max Act: 7.8527. Min Act: -0.1700
Data Index: 7805674 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8527. Min Range: -7.8527
Max Act: 7.7277. Min Act: -0.1700
Data Index: 7279896 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8527. Min Range: -7.8527
Max Act: 7.5715. Min Act: -0.1700
Data Index: 4078101 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8527. Min Range: -7.8527
Max Act: 7.5715. Min Act: -0.1700
Data Index: 218923 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8527. Min Range: -7.8527
Max Act: 7.6027. Min Act: -0.1700
Data Index: 2352249 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8527. Min Range: -7.8527
Max Act: 7.5715. Min Act: -0.1700
Data Index: 7155776 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8527. Min Range: -7.8527
Max Act: 7.5090. Min Act: -0.1700
Data Index: 1055971 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8527. Min Range: -7.8527
Max Act: 7.4465. Min Act: -0.1700
Data Index: 4184815 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8527. Min Range: -7.8527
Max Act: 7.4152. Min Act: -0.1700
Data Index: 6416537 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8527. Min Range: -7.8527
Max Act: 7.3840. Min Act: -0.1700
Data Index: 5885536 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8527. Min Range: -7.8527
Max Act: 7.3215. Min Act: -0.1700
Data Index: 6012624 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8527. Min Range: -7.8527
Max Act: 7.3215. Min Act: -0.1700
Data Index: 3221267 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8527. Min Range: -7.8527
Max Act: 7.2902. Min Act: -0.1700
Data Index: 2223300 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8527. Min Range: -7.8527
Max Act: 7.1652. Min Act: -0.1700
Data Index: 5898907 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8527. Min Range: -7.8527
Max Act: 7.1340. Min Act: -0.1700
Data Index: 5692200 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8527. Min Range: -7.8527
Max Act: 7.1027. Min Act: -0.1700
Data Index: 6203812 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8527. Min Range: -7.8527
Max Act: 7.0715. Min Act: -0.1700
Data Index: 432656 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8527. Min Range: -7.8527
Max Act: 7.0715. Min Act: -0.1700
Data Index: 864778 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8527. Min Range: -7.8527
Max Act: 7.0715. Min Act: -0.1700
Data Index: 7627502 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8527. Min Range: -7.8527
Max Act: 7.0715. Min Act: -0.1700
Data Index: 6422157 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #19