Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4828 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1736. Min Range: -8.1736
Max Act: 8.1736. Min Act: -0.1700
Data Index: 5518934 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1736. Min Range: -8.1736
Max Act: 8.1736. Min Act: -0.1700
Data Index: 535478 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1736. Min Range: -8.1736
Max Act: 7.8611. Min Act: -0.1700
Data Index: 2569999 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1736. Min Range: -8.1736
Max Act: 7.7361. Min Act: -0.1700
Data Index: 7867311 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1736. Min Range: -8.1736
Max Act: 7.7986. Min Act: -0.1700
Data Index: 8432153 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1736. Min Range: -8.1736
Max Act: 7.6736. Min Act: -0.1700
Data Index: 7461005 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1736. Min Range: -8.1736
Max Act: 7.6736. Min Act: -0.1700
Data Index: 2636920 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1736. Min Range: -8.1736
Max Act: 7.6111. Min Act: -0.1700
Data Index: 3664656 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1736. Min Range: -8.1736
Max Act: 7.6111. Min Act: -0.1700
Data Index: 4709535 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1736. Min Range: -8.1736
Max Act: 7.5486. Min Act: -0.1700
Data Index: 3194692 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1736. Min Range: -8.1736
Max Act: 7.6111. Min Act: -0.1700
Data Index: 6809835 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1736. Min Range: -8.1736
Max Act: 7.5486. Min Act: -0.1700
Data Index: 2750666 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1736. Min Range: -8.1736
Max Act: 7.5486. Min Act: -0.1700
Data Index: 3996554 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1736. Min Range: -8.1736
Max Act: 7.5173. Min Act: -0.1700
Data Index: 3434594 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1736. Min Range: -8.1736
Max Act: 7.4861. Min Act: -0.1700
Data Index: 2904139 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1736. Min Range: -8.1736
Max Act: 7.4548. Min Act: -0.1700
Data Index: 8109161 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1736. Min Range: -8.1736
Max Act: 7.4548. Min Act: -0.1700
Data Index: 4345348 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1736. Min Range: -8.1736
Max Act: 7.4548. Min Act: -0.1700
Data Index: 5432604 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1736. Min Range: -8.1736
Max Act: 7.4236. Min Act: -0.1700
Data Index: 3187260 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1736. Min Range: -8.1736
Max Act: 7.4236. Min Act: -0.1700
Data Index: 7471531 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #19