Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2852 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1861. Min Range: -4.1861
Max Act: 4.1861. Min Act: -0.1700
Data Index: 7492892 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1861. Min Range: -4.1861
Max Act: 3.9048. Min Act: -0.1700
Data Index: 3769635 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1861. Min Range: -4.1861
Max Act: 3.8735. Min Act: -0.1700
Data Index: 5083019 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1861. Min Range: -4.1861
Max Act: 3.8735. Min Act: -0.1700
Data Index: 4870459 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1861. Min Range: -4.1861
Max Act: 3.8735. Min Act: -0.1700
Data Index: 4094126 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1861. Min Range: -4.1861
Max Act: 3.8422. Min Act: -0.1700
Data Index: 5350073 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1861. Min Range: -4.1861
Max Act: 3.8422. Min Act: -0.1700
Data Index: 293611 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1861. Min Range: -4.1861
Max Act: 3.8266. Min Act: -0.1700
Data Index: 2947068 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1861. Min Range: -4.1861
Max Act: 3.8110. Min Act: -0.1700
Data Index: 4211073 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1861. Min Range: -4.1861
Max Act: 3.8110. Min Act: -0.1700
Data Index: 1102190 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1861. Min Range: -4.1861
Max Act: 3.7953. Min Act: -0.1700
Data Index: 5350072 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1861. Min Range: -4.1861
Max Act: 3.7797. Min Act: -0.1700
Data Index: 8712444 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1861. Min Range: -4.1861
Max Act: 3.7640. Min Act: -0.1700
Data Index: 8393533 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1861. Min Range: -4.1861
Max Act: 3.7640. Min Act: -0.1700
Data Index: 2903018 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1861. Min Range: -4.1861
Max Act: 3.7328. Min Act: -0.1700
Data Index: 6485693 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1861. Min Range: -4.1861
Max Act: 3.7484. Min Act: -0.1700
Data Index: 2143601 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1861. Min Range: -4.1861
Max Act: 3.7640. Min Act: -0.1700
Data Index: 7784111 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1861. Min Range: -4.1861
Max Act: 3.7484. Min Act: -0.1700
Data Index: 7895388 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1861. Min Range: -4.1861
Max Act: 3.7640. Min Act: -0.1700
Data Index: 1271360 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1861. Min Range: -4.1861
Max Act: 3.7328. Min Act: -0.1700
Data Index: 5540734 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #19