Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6381 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8358. Min Range: -3.8358
Max Act: 3.8358. Min Act: -0.1700
Data Index: 1719004 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8358. Min Range: -3.8358
Max Act: 3.7732. Min Act: -0.1700
Data Index: 160299 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8358. Min Range: -3.8358
Max Act: 3.7732. Min Act: -0.1700
Data Index: 7937562 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8358. Min Range: -3.8358
Max Act: 3.7263. Min Act: -0.1700
Data Index: 3258351 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8358. Min Range: -3.8358
Max Act: 3.7107. Min Act: -0.1700
Data Index: 777467 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8358. Min Range: -3.8358
Max Act: 3.7107. Min Act: -0.1700
Data Index: 96513 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8358. Min Range: -3.8358
Max Act: 3.7107. Min Act: -0.1700
Data Index: 3471013 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8358. Min Range: -3.8358
Max Act: 3.6637. Min Act: -0.1700
Data Index: 6066986 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8358. Min Range: -3.8358
Max Act: 3.6637. Min Act: -0.1700
Data Index: 8774598 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8358. Min Range: -3.8358
Max Act: 3.6637. Min Act: -0.1700
Data Index: 4329213 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8358. Min Range: -3.8358
Max Act: 3.6481. Min Act: -0.1700
Data Index: 8372878 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8358. Min Range: -3.8358
Max Act: 3.6481. Min Act: -0.1700
Data Index: 6880636 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8358. Min Range: -3.8358
Max Act: 3.6168. Min Act: -0.1700
Data Index: 6424107 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8358. Min Range: -3.8358
Max Act: 3.6324. Min Act: -0.1700
Data Index: 1200386 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8358. Min Range: -3.8358
Max Act: 3.6168. Min Act: -0.1700
Data Index: 4504075 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8358. Min Range: -3.8358
Max Act: 3.6168. Min Act: -0.1700
Data Index: 1580034 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8358. Min Range: -3.8358
Max Act: 3.6168. Min Act: -0.1700
Data Index: 1580039 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8358. Min Range: -3.8358
Max Act: 3.6011. Min Act: -0.1700
Data Index: 2837178 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8358. Min Range: -3.8358
Max Act: 3.6011. Min Act: -0.1700
Data Index: 7365415 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8358. Min Range: -3.8358
Max Act: 3.6011. Min Act: -0.1700
Data Index: 8005706 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #19