Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 460 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4497. Min Range: -7.4497
Max Act: 7.4497. Min Act: -0.1700
Data Index: 5788576 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4497. Min Range: -7.4497
Max Act: 7.2310. Min Act: -0.1700
Data Index: 5606914 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4497. Min Range: -7.4497
Max Act: 7.2310. Min Act: -0.1700
Data Index: 7939481 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4497. Min Range: -7.4497
Max Act: 7.1997. Min Act: -0.1700
Data Index: 5618465 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4497. Min Range: -7.4497
Max Act: 7.1997. Min Act: -0.1700
Data Index: 3877576 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4497. Min Range: -7.4497
Max Act: 7.1372. Min Act: -0.1700
Data Index: 4355459 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4497. Min Range: -7.4497
Max Act: 7.1060. Min Act: -0.1700
Data Index: 3098661 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4497. Min Range: -7.4497
Max Act: 7.1372. Min Act: -0.1700
Data Index: 7895634 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4497. Min Range: -7.4497
Max Act: 7.1372. Min Act: -0.1700
Data Index: 833441 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4497. Min Range: -7.4497
Max Act: 7.1060. Min Act: -0.1700
Data Index: 6752670 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4497. Min Range: -7.4497
Max Act: 7.0747. Min Act: -0.1700
Data Index: 8650358 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4497. Min Range: -7.4497
Max Act: 7.0435. Min Act: -0.1700
Data Index: 5216879 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4497. Min Range: -7.4497
Max Act: 7.0122. Min Act: -0.1700
Data Index: 1439143 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4497. Min Range: -7.4497
Max Act: 7.0435. Min Act: -0.1700
Data Index: 7692344 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4497. Min Range: -7.4497
Max Act: 7.0122. Min Act: -0.1700
Data Index: 3447623 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4497. Min Range: -7.4497
Max Act: 7.0122. Min Act: -0.1700
Data Index: 8303889 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4497. Min Range: -7.4497
Max Act: 7.0122. Min Act: -0.1700
Data Index: 5036800 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4497. Min Range: -7.4497
Max Act: 6.9810. Min Act: -0.1700
Data Index: 2554383 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4497. Min Range: -7.4497
Max Act: 6.9810. Min Act: -0.1700
Data Index: 4308167 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4497. Min Range: -7.4497
Max Act: 6.9185. Min Act: -0.1700
Data Index: 4341928 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #19