Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3272 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4743. Min Range: -6.4743
Max Act: 6.4743. Min Act: -0.1700
Data Index: 3070258 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4743. Min Range: -6.4743
Max Act: 6.3493. Min Act: -0.1700
Data Index: 4169408 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4743. Min Range: -6.4743
Max Act: 6.2243. Min Act: -0.1700
Data Index: 5122100 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4743. Min Range: -6.4743
Max Act: 6.0993. Min Act: -0.1700
Data Index: 5663536 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4743. Min Range: -6.4743
Max Act: 6.0056. Min Act: -0.1700
Data Index: 2425463 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4743. Min Range: -6.4743
Max Act: 5.9431. Min Act: -0.1700
Data Index: 7756564 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4743. Min Range: -6.4743
Max Act: 5.9431. Min Act: -0.1700
Data Index: 6008675 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4743. Min Range: -6.4743
Max Act: 5.8806. Min Act: -0.1700
Data Index: 1788420 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4743. Min Range: -6.4743
Max Act: 5.8493. Min Act: -0.1700
Data Index: 8368374 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4743. Min Range: -6.4743
Max Act: 5.8493. Min Act: -0.1700
Data Index: 704770 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4743. Min Range: -6.4743
Max Act: 5.8493. Min Act: -0.1700
Data Index: 6683230 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4743. Min Range: -6.4743
Max Act: 5.8181. Min Act: -0.1700
Data Index: 3089400 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4743. Min Range: -6.4743
Max Act: 5.8181. Min Act: -0.1700
Data Index: 6973997 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4743. Min Range: -6.4743
Max Act: 5.7868. Min Act: -0.1700
Data Index: 3818906 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4743. Min Range: -6.4743
Max Act: 5.8181. Min Act: -0.1700
Data Index: 2972881 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4743. Min Range: -6.4743
Max Act: 5.7868. Min Act: -0.1700
Data Index: 1058004 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4743. Min Range: -6.4743
Max Act: 5.7868. Min Act: -0.1700
Data Index: 6967561 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4743. Min Range: -6.4743
Max Act: 5.7868. Min Act: -0.1700
Data Index: 2734704 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4743. Min Range: -6.4743
Max Act: 5.7243. Min Act: -0.1700
Data Index: 2350542 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4743. Min Range: -6.4743
Max Act: 5.7556. Min Act: -0.1700
Data Index: 7595215 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19