Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1435 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6132. Min Range: -6.6132
Max Act: 6.6132. Min Act: -0.1700
Data Index: 6100145 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6132. Min Range: -6.6132
Max Act: 6.4257. Min Act: -0.1700
Data Index: 8238365 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6132. Min Range: -6.6132
Max Act: 6.3944. Min Act: -0.1700
Data Index: 4421278 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6132. Min Range: -6.6132
Max Act: 6.2694. Min Act: -0.1700
Data Index: 6791475 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6132. Min Range: -6.6132
Max Act: 6.2694. Min Act: -0.1700
Data Index: 5573788 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6132. Min Range: -6.6132
Max Act: 6.2069. Min Act: -0.1700
Data Index: 4181120 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6132. Min Range: -6.6132
Max Act: 6.1444. Min Act: -0.1700
Data Index: 671488 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6132. Min Range: -6.6132
Max Act: 6.0819. Min Act: -0.1700
Data Index: 4766892 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6132. Min Range: -6.6132
Max Act: 6.0819. Min Act: -0.1700
Data Index: 8827564 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6132. Min Range: -6.6132
Max Act: 6.0507. Min Act: -0.1700
Data Index: 8709658 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6132. Min Range: -6.6132
Max Act: 6.0194. Min Act: -0.1700
Data Index: 2999399 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6132. Min Range: -6.6132
Max Act: 6.0819. Min Act: -0.1700
Data Index: 1280316 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6132. Min Range: -6.6132
Max Act: 5.9882. Min Act: -0.1700
Data Index: 2432553 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6132. Min Range: -6.6132
Max Act: 6.0194. Min Act: -0.1700
Data Index: 7039429 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6132. Min Range: -6.6132
Max Act: 5.9882. Min Act: -0.1700
Data Index: 4142483 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6132. Min Range: -6.6132
Max Act: 5.9569. Min Act: -0.1700
Data Index: 4802223 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6132. Min Range: -6.6132
Max Act: 5.9569. Min Act: -0.1700
Data Index: 421412 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6132. Min Range: -6.6132
Max Act: 5.9569. Min Act: -0.1700
Data Index: 6757516 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6132. Min Range: -6.6132
Max Act: 5.9257. Min Act: -0.1700
Data Index: 5586647 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6132. Min Range: -6.6132
Max Act: 5.9257. Min Act: -0.1700
Data Index: 489530 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #19