Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4774 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4844. Min Range: -7.4844
Max Act: 7.4844. Min Act: -0.1700
Data Index: 3822001 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4844. Min Range: -7.4844
Max Act: 7.4219. Min Act: -0.1700
Data Index: 6559669 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4844. Min Range: -7.4844
Max Act: 7.4219. Min Act: -0.1700
Data Index: 5519055 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4844. Min Range: -7.4844
Max Act: 7.3594. Min Act: -0.1700
Data Index: 1228305 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4844. Min Range: -7.4844
Max Act: 7.2344. Min Act: -0.1700
Data Index: 3076159 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4844. Min Range: -7.4844
Max Act: 7.2344. Min Act: -0.1700
Data Index: 4648201 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4844. Min Range: -7.4844
Max Act: 7.2344. Min Act: -0.1700
Data Index: 4355285 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4844. Min Range: -7.4844
Max Act: 7.2344. Min Act: -0.1700
Data Index: 3512155 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4844. Min Range: -7.4844
Max Act: 7.2032. Min Act: -0.1700
Data Index: 1467542 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4844. Min Range: -7.4844
Max Act: 7.2032. Min Act: -0.1700
Data Index: 2645686 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4844. Min Range: -7.4844
Max Act: 7.1719. Min Act: -0.1700
Data Index: 4306519 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4844. Min Range: -7.4844
Max Act: 7.1407. Min Act: -0.1700
Data Index: 2670473 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4844. Min Range: -7.4844
Max Act: 7.1719. Min Act: -0.1700
Data Index: 6054117 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4844. Min Range: -7.4844
Max Act: 7.1719. Min Act: -0.1700
Data Index: 844649 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4844. Min Range: -7.4844
Max Act: 7.1719. Min Act: -0.1700
Data Index: 6182687 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4844. Min Range: -7.4844
Max Act: 7.1719. Min Act: -0.1700
Data Index: 7627798 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4844. Min Range: -7.4844
Max Act: 7.1407. Min Act: -0.1700
Data Index: 5367355 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4844. Min Range: -7.4844
Max Act: 7.1407. Min Act: -0.1700
Data Index: 1193275 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4844. Min Range: -7.4844
Max Act: 7.1094. Min Act: -0.1700
Data Index: 414000 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4844. Min Range: -7.4844
Max Act: 7.1094. Min Act: -0.1700
Data Index: 6627161 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #19