Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 284 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6919. Min Range: -4.6919
Max Act: 4.6919. Min Act: -0.1700
Data Index: 748329 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6919. Min Range: -4.6919
Max Act: 4.5669. Min Act: -0.1700
Data Index: 2032867 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6919. Min Range: -4.6919
Max Act: 4.5669. Min Act: -0.1700
Data Index: 8670828 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6919. Min Range: -4.6919
Max Act: 4.5357. Min Act: -0.1700
Data Index: 8333779 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6919. Min Range: -4.6919
Max Act: 4.4732. Min Act: -0.1700
Data Index: 2721533 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6919. Min Range: -4.6919
Max Act: 4.4419. Min Act: -0.1700
Data Index: 1690963 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6919. Min Range: -4.6919
Max Act: 4.4419. Min Act: -0.1700
Data Index: 2379245 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6919. Min Range: -4.6919
Max Act: 4.3794. Min Act: -0.1700
Data Index: 3999184 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6919. Min Range: -4.6919
Max Act: 4.3794. Min Act: -0.1700
Data Index: 7754786 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6919. Min Range: -4.6919
Max Act: 4.3794. Min Act: -0.1700
Data Index: 4176315 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6919. Min Range: -4.6919
Max Act: 4.3169. Min Act: -0.1700
Data Index: 4061328 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6919. Min Range: -4.6919
Max Act: 4.2857. Min Act: -0.1700
Data Index: 3187875 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6919. Min Range: -4.6919
Max Act: 4.2857. Min Act: -0.1700
Data Index: 2752398 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6919. Min Range: -4.6919
Max Act: 4.2857. Min Act: -0.1700
Data Index: 4388145 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6919. Min Range: -4.6919
Max Act: 4.3169. Min Act: -0.1700
Data Index: 2586512 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6919. Min Range: -4.6919
Max Act: 4.2544. Min Act: -0.1700
Data Index: 6293970 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6919. Min Range: -4.6919
Max Act: 4.2857. Min Act: -0.1700
Data Index: 6448378 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6919. Min Range: -4.6919
Max Act: 4.2544. Min Act: -0.1700
Data Index: 5830957 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6919. Min Range: -4.6919
Max Act: 4.2857. Min Act: -0.1700
Data Index: 8726799 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6919. Min Range: -4.6919
Max Act: 4.2857. Min Act: -0.1700
Data Index: 4067151 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19