Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5330 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4098. Min Range: -8.4098
Max Act: 8.4098. Min Act: -0.1700
Data Index: 28641 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4098. Min Range: -8.4098
Max Act: 8.0348. Min Act: -0.1700
Data Index: 793876 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4098. Min Range: -8.4098
Max Act: 7.9723. Min Act: -0.1700
Data Index: 8667717 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4098. Min Range: -8.4098
Max Act: 7.9098. Min Act: -0.1700
Data Index: 3576361 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4098. Min Range: -8.4098
Max Act: 7.8473. Min Act: -0.1700
Data Index: 6351893 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4098. Min Range: -8.4098
Max Act: 7.7848. Min Act: -0.1700
Data Index: 6413689 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4098. Min Range: -8.4098
Max Act: 7.7223. Min Act: -0.1700
Data Index: 1716535 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4098. Min Range: -8.4098
Max Act: 7.6911. Min Act: -0.1700
Data Index: 2934219 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4098. Min Range: -8.4098
Max Act: 7.6598. Min Act: -0.1700
Data Index: 465704 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4098. Min Range: -8.4098
Max Act: 7.6598. Min Act: -0.1700
Data Index: 1835912 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4098. Min Range: -8.4098
Max Act: 7.6598. Min Act: -0.1700
Data Index: 4257937 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4098. Min Range: -8.4098
Max Act: 7.6286. Min Act: -0.1700
Data Index: 4957865 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4098. Min Range: -8.4098
Max Act: 7.6286. Min Act: -0.1700
Data Index: 8238839 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4098. Min Range: -8.4098
Max Act: 7.6286. Min Act: -0.1700
Data Index: 6041504 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4098. Min Range: -8.4098
Max Act: 7.5973. Min Act: -0.1700
Data Index: 8186877 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4098. Min Range: -8.4098
Max Act: 7.5661. Min Act: -0.1700
Data Index: 4999715 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4098. Min Range: -8.4098
Max Act: 7.5661. Min Act: -0.1700
Data Index: 8334392 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4098. Min Range: -8.4098
Max Act: 7.5661. Min Act: -0.1700
Data Index: 7690864 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4098. Min Range: -8.4098
Max Act: 7.5973. Min Act: -0.1700
Data Index: 6603457 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4098. Min Range: -8.4098
Max Act: 7.5661. Min Act: -0.1700
Data Index: 4747602 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #19