Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3650 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9902. Min Range: -4.9902
Max Act: 4.9902. Min Act: -0.1700
Data Index: 7841891 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9902. Min Range: -4.9902
Max Act: 4.9902. Min Act: -0.1700
Data Index: 6322981 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9902. Min Range: -4.9902
Max Act: 4.9277. Min Act: -0.1700
Data Index: 2489332 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9902. Min Range: -4.9902
Max Act: 4.9277. Min Act: -0.1700
Data Index: 6727958 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9902. Min Range: -4.9902
Max Act: 4.8340. Min Act: -0.1700
Data Index: 7850413 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9902. Min Range: -4.9902
Max Act: 4.5527. Min Act: -0.1700
Data Index: 5616064 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9902. Min Range: -4.9902
Max Act: 4.5215. Min Act: -0.1700
Data Index: 7884254 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9902. Min Range: -4.9902
Max Act: 4.5215. Min Act: -0.1700
Data Index: 786831 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9902. Min Range: -4.9902
Max Act: 4.4902. Min Act: -0.1700
Data Index: 2144586 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9902. Min Range: -4.9902
Max Act: 4.4590. Min Act: -0.1700
Data Index: 4375700 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9902. Min Range: -4.9902
Max Act: 4.4590. Min Act: -0.1700
Data Index: 761003 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9902. Min Range: -4.9902
Max Act: 4.3965. Min Act: -0.1700
Data Index: 1366794 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9902. Min Range: -4.9902
Max Act: 4.3965. Min Act: -0.1700
Data Index: 652373 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9902. Min Range: -4.9902
Max Act: 4.3965. Min Act: -0.1700
Data Index: 6516338 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9902. Min Range: -4.9902
Max Act: 4.3965. Min Act: -0.1700
Data Index: 2106734 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9902. Min Range: -4.9902
Max Act: 4.3652. Min Act: -0.1700
Data Index: 7098385 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9902. Min Range: -4.9902
Max Act: 4.3652. Min Act: -0.1700
Data Index: 7824095 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9902. Min Range: -4.9902
Max Act: 4.3340. Min Act: -0.1700
Data Index: 5350637 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9902. Min Range: -4.9902
Max Act: 4.3652. Min Act: -0.1700
Data Index: 586584 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9902. Min Range: -4.9902
Max Act: 4.3340. Min Act: -0.1700
Data Index: 1017583 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19