Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3074 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0446. Min Range: -6.0446
Max Act: 6.0446. Min Act: -0.1700
Data Index: 7019633 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0446. Min Range: -6.0446
Max Act: 6.0133. Min Act: -0.1700
Data Index: 6008929 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0446. Min Range: -6.0446
Max Act: 5.7946. Min Act: -0.1700
Data Index: 2416061 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0446. Min Range: -6.0446
Max Act: 5.7633. Min Act: -0.1700
Data Index: 4884654 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0446. Min Range: -6.0446
Max Act: 5.7008. Min Act: -0.1700
Data Index: 6651081 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0446. Min Range: -6.0446
Max Act: 5.6696. Min Act: -0.1700
Data Index: 8788126 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0446. Min Range: -6.0446
Max Act: 5.6696. Min Act: -0.1696
Data Index: 6670407 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0446. Min Range: -6.0446
Max Act: 5.7008. Min Act: -0.1700
Data Index: 4086320 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0446. Min Range: -6.0446
Max Act: 5.6383. Min Act: -0.1700
Data Index: 6128348 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0446. Min Range: -6.0446
Max Act: 5.5758. Min Act: -0.1700
Data Index: 3820357 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0446. Min Range: -6.0446
Max Act: 5.5446. Min Act: -0.1700
Data Index: 810668 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0446. Min Range: -6.0446
Max Act: 5.5133. Min Act: -0.1694
Data Index: 1791547 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0446. Min Range: -6.0446
Max Act: 5.4821. Min Act: -0.1696
Data Index: 2703288 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0446. Min Range: -6.0446
Max Act: 5.4821. Min Act: -0.1700
Data Index: 2792697 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0446. Min Range: -6.0446
Max Act: 5.4508. Min Act: -0.1700
Data Index: 8663723 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0446. Min Range: -6.0446
Max Act: 5.4508. Min Act: -0.1700
Data Index: 5531770 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0446. Min Range: -6.0446
Max Act: 5.3883. Min Act: -0.1700
Data Index: 3545130 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0446. Min Range: -6.0446
Max Act: 5.3571. Min Act: -0.1700
Data Index: 3279554 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0446. Min Range: -6.0446
Max Act: 5.3258. Min Act: -0.1700
Data Index: 7996619 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0446. Min Range: -6.0446
Max Act: 5.3571. Min Act: -0.1700
Data Index: 615241 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #19