Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 369 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3009. Min Range: -5.3009
Max Act: 5.3009. Min Act: -0.1700
Data Index: 6469934 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3009. Min Range: -5.3009
Max Act: 5.2696. Min Act: -0.1700
Data Index: 5180548 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3009. Min Range: -5.3009
Max Act: 5.1759. Min Act: -0.1700
Data Index: 222604 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3009. Min Range: -5.3009
Max Act: 5.1759. Min Act: -0.1700
Data Index: 6384626 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3009. Min Range: -5.3009
Max Act: 5.1446. Min Act: -0.1700
Data Index: 3670607 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3009. Min Range: -5.3009
Max Act: 5.0821. Min Act: -0.1700
Data Index: 4427815 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3009. Min Range: -5.3009
Max Act: 5.0821. Min Act: -0.1700
Data Index: 2538609 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3009. Min Range: -5.3009
Max Act: 5.0821. Min Act: -0.1700
Data Index: 4446201 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3009. Min Range: -5.3009
Max Act: 5.0509. Min Act: -0.1700
Data Index: 406299 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3009. Min Range: -5.3009
Max Act: 5.0509. Min Act: -0.1700
Data Index: 883977 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3009. Min Range: -5.3009
Max Act: 5.0509. Min Act: -0.1700
Data Index: 5176266 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3009. Min Range: -5.3009
Max Act: 5.0196. Min Act: -0.1700
Data Index: 7057406 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3009. Min Range: -5.3009
Max Act: 5.0196. Min Act: -0.1700
Data Index: 6176076 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3009. Min Range: -5.3009
Max Act: 5.0196. Min Act: -0.1700
Data Index: 6875503 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3009. Min Range: -5.3009
Max Act: 5.0196. Min Act: -0.1700
Data Index: 6469937 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3009. Min Range: -5.3009
Max Act: 4.9884. Min Act: -0.1700
Data Index: 2367532 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3009. Min Range: -5.3009
Max Act: 4.9884. Min Act: -0.1700
Data Index: 1444845 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3009. Min Range: -5.3009
Max Act: 4.9884. Min Act: -0.1700
Data Index: 6220143 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3009. Min Range: -5.3009
Max Act: 5.0196. Min Act: -0.1700
Data Index: 959215 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3009. Min Range: -5.3009
Max Act: 4.9884. Min Act: -0.1700
Data Index: 290544 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #19