Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4615 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0321. Min Range: -5.0321
Max Act: 5.0321. Min Act: -0.1700
Data Index: 3966823 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0321. Min Range: -5.0321
Max Act: 5.0321. Min Act: -0.1697
Data Index: 8607404 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0321. Min Range: -5.0321
Max Act: 4.9696. Min Act: -0.1700
Data Index: 577397 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0321. Min Range: -5.0321
Max Act: 4.9384. Min Act: -0.1700
Data Index: 3234220 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0321. Min Range: -5.0321
Max Act: 4.9071. Min Act: -0.1700
Data Index: 7137826 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0321. Min Range: -5.0321
Max Act: 4.8759. Min Act: -0.1700
Data Index: 3090295 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0321. Min Range: -5.0321
Max Act: 4.8446. Min Act: -0.1700
Data Index: 5520245 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0321. Min Range: -5.0321
Max Act: 4.8446. Min Act: -0.1700
Data Index: 5532234 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0321. Min Range: -5.0321
Max Act: 4.8134. Min Act: -0.1700
Data Index: 2822901 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0321. Min Range: -5.0321
Max Act: 4.7509. Min Act: -0.1700
Data Index: 2739864 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0321. Min Range: -5.0321
Max Act: 4.7821. Min Act: -0.1700
Data Index: 2403414 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0321. Min Range: -5.0321
Max Act: 4.7821. Min Act: -0.1700
Data Index: 901126 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0321. Min Range: -5.0321
Max Act: 4.7509. Min Act: -0.1700
Data Index: 4926667 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0321. Min Range: -5.0321
Max Act: 4.7196. Min Act: -0.1700
Data Index: 7620235 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0321. Min Range: -5.0321
Max Act: 4.7196. Min Act: -0.1700
Data Index: 5007645 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0321. Min Range: -5.0321
Max Act: 4.7196. Min Act: -0.1700
Data Index: 7741288 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0321. Min Range: -5.0321
Max Act: 4.6884. Min Act: -0.1700
Data Index: 5590363 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0321. Min Range: -5.0321
Max Act: 4.6571. Min Act: -0.1700
Data Index: 4257247 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0321. Min Range: -5.0321
Max Act: 4.6884. Min Act: -0.1700
Data Index: 1158368 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0321. Min Range: -5.0321
Max Act: 4.6884. Min Act: -0.1700
Data Index: 6346030 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #19