Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3251 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0296. Min Range: -5.0296
Max Act: 5.0296. Min Act: -0.1700
Data Index: 706484 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0296. Min Range: -5.0296
Max Act: 4.9984. Min Act: -0.1700
Data Index: 8389470 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0296. Min Range: -5.0296
Max Act: 4.9984. Min Act: -0.1700
Data Index: 4681877 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0296. Min Range: -5.0296
Max Act: 4.9671. Min Act: -0.1700
Data Index: 3216208 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0296. Min Range: -5.0296
Max Act: 4.9671. Min Act: -0.1700
Data Index: 8586677 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0296. Min Range: -5.0296
Max Act: 4.9671. Min Act: -0.1700
Data Index: 1722789 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0296. Min Range: -5.0296
Max Act: 4.9359. Min Act: -0.1700
Data Index: 706483 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0296. Min Range: -5.0296
Max Act: 4.9046. Min Act: -0.1700
Data Index: 7291201 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0296. Min Range: -5.0296
Max Act: 4.9046. Min Act: -0.1700
Data Index: 5012337 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0296. Min Range: -5.0296
Max Act: 4.9046. Min Act: -0.1700
Data Index: 4231224 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0296. Min Range: -5.0296
Max Act: 4.9046. Min Act: -0.1700
Data Index: 4865073 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0296. Min Range: -5.0296
Max Act: 4.9046. Min Act: -0.1700
Data Index: 5650418 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0296. Min Range: -5.0296
Max Act: 4.8734. Min Act: -0.1700
Data Index: 706487 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0296. Min Range: -5.0296
Max Act: 4.8734. Min Act: -0.1700
Data Index: 706482 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0296. Min Range: -5.0296
Max Act: 4.9046. Min Act: -0.1700
Data Index: 6937794 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0296. Min Range: -5.0296
Max Act: 4.8734. Min Act: -0.1700
Data Index: 5219327 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0296. Min Range: -5.0296
Max Act: 4.8421. Min Act: -0.1700
Data Index: 1722791 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0296. Min Range: -5.0296
Max Act: 4.8421. Min Act: -0.1700
Data Index: 2964879 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0296. Min Range: -5.0296
Max Act: 4.8421. Min Act: -0.1700
Data Index: 8078230 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0296. Min Range: -5.0296
Max Act: 4.8734. Min Act: -0.1700
Data Index: 706485 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #19