Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2664 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1578. Min Range: -8.1578
Max Act: 8.1578. Min Act: -0.1700
Data Index: 2699940 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1578. Min Range: -8.1578
Max Act: 7.9391. Min Act: -0.1700
Data Index: 2446524 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1578. Min Range: -8.1578
Max Act: 7.5641. Min Act: -0.1700
Data Index: 688154 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1578. Min Range: -8.1578
Max Act: 7.4703. Min Act: -0.1700
Data Index: 2287626 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1578. Min Range: -8.1578
Max Act: 7.3453. Min Act: -0.1700
Data Index: 6282455 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1578. Min Range: -8.1578
Max Act: 7.2828. Min Act: -0.1700
Data Index: 546152 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1578. Min Range: -8.1578
Max Act: 7.2516. Min Act: -0.1700
Data Index: 4610878 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1578. Min Range: -8.1578
Max Act: 7.2516. Min Act: -0.1700
Data Index: 7730630 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1578. Min Range: -8.1578
Max Act: 7.2516. Min Act: -0.1700
Data Index: 6805958 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1578. Min Range: -8.1578
Max Act: 7.2516. Min Act: -0.1700
Data Index: 7172593 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1578. Min Range: -8.1578
Max Act: 7.2203. Min Act: -0.1700
Data Index: 6805960 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1578. Min Range: -8.1578
Max Act: 7.1891. Min Act: -0.1700
Data Index: 4359773 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1578. Min Range: -8.1578
Max Act: 7.1891. Min Act: -0.1700
Data Index: 8283664 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1578. Min Range: -8.1578
Max Act: 7.1578. Min Act: -0.1700
Data Index: 3931501 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1578. Min Range: -8.1578
Max Act: 7.1578. Min Act: -0.1700
Data Index: 5648831 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1578. Min Range: -8.1578
Max Act: 7.1266. Min Act: -0.1700
Data Index: 7279862 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1578. Min Range: -8.1578
Max Act: 7.1266. Min Act: -0.1700
Data Index: 4459454 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1578. Min Range: -8.1578
Max Act: 7.1266. Min Act: -0.1700
Data Index: 7209131 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1578. Min Range: -8.1578
Max Act: 7.0953. Min Act: -0.1700
Data Index: 6587124 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1578. Min Range: -8.1578
Max Act: 7.0953. Min Act: -0.1700
Data Index: 4606242 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #19