Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3278 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2709. Min Range: -6.2709
Max Act: 6.2709. Min Act: -0.1700
Data Index: 3099883 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2709. Min Range: -6.2709
Max Act: 6.1146. Min Act: -0.1700
Data Index: 1585248 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2709. Min Range: -6.2709
Max Act: 6.0834. Min Act: -0.1700
Data Index: 8459984 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2709. Min Range: -6.2709
Max Act: 6.0521. Min Act: -0.1700
Data Index: 3128323 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2709. Min Range: -6.2709
Max Act: 6.0834. Min Act: -0.1700
Data Index: 5129634 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2709. Min Range: -6.2709
Max Act: 6.0209. Min Act: -0.1700
Data Index: 6851570 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2709. Min Range: -6.2709
Max Act: 6.0521. Min Act: -0.1700
Data Index: 2305491 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.9896. Min Act: -0.1700
Data Index: 1733681 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.9896. Min Act: -0.1700
Data Index: 7222107 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.9896. Min Act: -0.1700
Data Index: 641931 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.9271. Min Act: -0.1700
Data Index: 333687 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.9271. Min Act: -0.1700
Data Index: 3839879 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.9584. Min Act: -0.1700
Data Index: 3933777 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.9584. Min Act: -0.1700
Data Index: 4496407 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.9584. Min Act: -0.1700
Data Index: 7659958 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.9584. Min Act: -0.1700
Data Index: 8212360 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.9584. Min Act: -0.1700
Data Index: 3224718 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.9271. Min Act: -0.1700
Data Index: 4196231 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.8959. Min Act: -0.1700
Data Index: 523937 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.9271. Min Act: -0.1700
Data Index: 4105916 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #19