Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4578 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6418. Min Range: -7.6418
Max Act: 7.6418. Min Act: -0.1700
Data Index: 7326547 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6418. Min Range: -7.6418
Max Act: 7.5793. Min Act: -0.1700
Data Index: 5777799 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6418. Min Range: -7.6418
Max Act: 7.5168. Min Act: -0.1700
Data Index: 4417312 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6418. Min Range: -7.6418
Max Act: 7.3293. Min Act: -0.1700
Data Index: 7242052 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6418. Min Range: -7.6418
Max Act: 7.2355. Min Act: -0.1700
Data Index: 5887573 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6418. Min Range: -7.6418
Max Act: 7.1418. Min Act: -0.1700
Data Index: 2926342 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6418. Min Range: -7.6418
Max Act: 7.1730. Min Act: -0.1700
Data Index: 5422457 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6418. Min Range: -7.6418
Max Act: 7.1730. Min Act: -0.1700
Data Index: 36487 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6418. Min Range: -7.6418
Max Act: 7.1418. Min Act: -0.1700
Data Index: 2249465 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6418. Min Range: -7.6418
Max Act: 7.1418. Min Act: -0.1700
Data Index: 6516894 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6418. Min Range: -7.6418
Max Act: 7.1418. Min Act: -0.1700
Data Index: 1278715 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6418. Min Range: -7.6418
Max Act: 7.1105. Min Act: -0.1700
Data Index: 6259658 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6418. Min Range: -7.6418
Max Act: 7.0793. Min Act: -0.1700
Data Index: 2034957 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6418. Min Range: -7.6418
Max Act: 7.0793. Min Act: -0.1700
Data Index: 3813891 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6418. Min Range: -7.6418
Max Act: 7.0793. Min Act: -0.1700
Data Index: 667946 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6418. Min Range: -7.6418
Max Act: 7.0793. Min Act: -0.1700
Data Index: 8134231 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6418. Min Range: -7.6418
Max Act: 7.0480. Min Act: -0.1700
Data Index: 8046199 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6418. Min Range: -7.6418
Max Act: 7.0168. Min Act: -0.1700
Data Index: 162368 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6418. Min Range: -7.6418
Max Act: 7.0168. Min Act: -0.1700
Data Index: 6607661 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6418. Min Range: -7.6418
Max Act: 6.9855. Min Act: -0.1700
Data Index: 5237444 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #19