Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2270 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9609. Min Range: -2.9609
Max Act: 2.9609. Min Act: -0.1700
Data Index: 5628491 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9609. Min Range: -2.9609
Max Act: 2.9451. Min Act: -0.1700
Data Index: 3094654 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9609. Min Range: -2.9609
Max Act: 2.9451. Min Act: -0.1700
Data Index: 6256360 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9609. Min Range: -2.9609
Max Act: 2.9134. Min Act: -0.1700
Data Index: 2122676 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9609. Min Range: -2.9609
Max Act: 2.9134. Min Act: -0.1700
Data Index: 636768 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9609. Min Range: -2.9609
Max Act: 2.8658. Min Act: -0.1700
Data Index: 17662 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9609. Min Range: -2.9609
Max Act: 2.8658. Min Act: -0.1700
Data Index: 557026 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9609. Min Range: -2.9609
Max Act: 2.8340. Min Act: -0.1700
Data Index: 8377148 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9609. Min Range: -2.9609
Max Act: 2.8499. Min Act: -0.1700
Data Index: 5157495 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9609. Min Range: -2.9609
Max Act: 2.8340. Min Act: -0.1700
Data Index: 6294431 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9609. Min Range: -2.9609
Max Act: 2.8181. Min Act: -0.1700
Data Index: 2218642 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9609. Min Range: -2.9609
Max Act: 2.8022. Min Act: -0.1700
Data Index: 4716769 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9609. Min Range: -2.9609
Max Act: 2.7863. Min Act: -0.1700
Data Index: 5711071 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9609. Min Range: -2.9609
Max Act: 2.8181. Min Act: -0.1700
Data Index: 1029007 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9609. Min Range: -2.9609
Max Act: 2.7703. Min Act: -0.1700
Data Index: 5088764 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9609. Min Range: -2.9609
Max Act: 2.7863. Min Act: -0.1700
Data Index: 6732411 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9609. Min Range: -2.9609
Max Act: 2.7863. Min Act: -0.1700
Data Index: 6768723 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9609. Min Range: -2.9609
Max Act: 2.7863. Min Act: -0.1700
Data Index: 6786170 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9609. Min Range: -2.9609
Max Act: 2.7863. Min Act: -0.1700
Data Index: 7640473 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9609. Min Range: -2.9609
Max Act: 2.7863. Min Act: -0.1700
Data Index: 1814294 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #19